Wiley

Journal of Field Robotics

Published by Wiley

Online ISSN: 1556-4967

·

Print ISSN: 1556-4959

Journal websiteAuthor guidelines

Top-read articles

372 reads in the past 30 days

FIGURE 1 | Robots can support various cleaning applications. A broad classification is provided in the figure.
FIGURE 3 | A sample floor-cleaning robot. Most of the floorcleaning robots are flat-, circular-, or cylindrical-shaped with openings for sensors. In addition, they perform cleaning autonomously with the vacuum cleaning method and hence no need of brushes. LiDAR, light detection and ranging. [Color figure can be viewed at wileyonlinelibrary.com]
FIGURE 4 | Robots used in industrial/commercial settings. Usually bigger in size with complex sensor systems, inbuilt tanks for water and soap, big brushes, and so forth. (a) Autonomous and (b) teleoperated. LiDAR, light detection and ranging. [Color figure can be viewed at wileyonlinelibrary.com]
FIGURE 5 | A floor mopping robot. [Color figure can be viewed at wileyonlinelibrary.com]
FIGURE 6 | The mechanisms, the technologies, and other features, which are part of staircase-cleaning robots. DL, deep learning; ML, machine learning. [Color figure can be viewed at wileyonlinelibrary.com]

+9

Cleaning Robots: A Review of Sensor Technologies and Intelligent Control Strategies for Cleaning

January 2025

·

724 Reads

·

11 Citations

·

Shree Rajesh Raagul Vadivel

·

Sai Smaran Kotaprolu

·

[...]

·

Gaurav Rudravaram
Download

Aims and scope


The Journal of Field Robotics is an applied robotics journal publishing impactful research on the fundamentals of robotics in unstructured and dynamic environments. We welcome theoretical and practical papers on robotics used in real-world applications such as construction, forestry, agriculture, mining, environment, nuclear, subsea, intelligent highways, healthcare, search and rescue, military, and space (orbital and planetary). We also cover technical and scientific topics such as sensing, mechanical design, computing architectures, learning and control, human-robot interaction, and security.

Recent articles


The Autonomous Route Planning Algorithm for Rock Drilling Manipulator Based on Collision Detection
  • Article
  • Publisher preview available

June 2025

In the field of high‐redundancy manipulators, specifically in the rock drilling manipulator domain, fast and efficient path planning is crucial. Therefore, this paper proposes an improved algorithm, v‐BI‐RRT, based on the BI‐RRT algorithm and oriented vector methods. In this algorithm, the nodes along one path are extended in the direction of the node coordinates of another path as the target direction. When the path collides with an obstacle, new node coordinates are generated using a random sampling method to bypass the obstacle. This approach enhances spatial search efficiency. For high‐redundancy manipulators like the rock drilling manipulator, self‐collision avoidance is a key component of collision‐free path planning. This paper uses oriented bounding boxes (OBB) and capsules to envelope the manipulator's body. Potential self‐collisions are detected in two stages: during the rapid detection phase, non‐colliding pairs are quickly excluded, and during the precise detection phase, the distance between the remaining potential collision pairs is calculated using Euclidean distance to find the shortest distance. Finally, the self‐collision detection algorithm is integrated into the v‐BI‐RRT algorithm. Simulations and experiments demonstrate that the algorithm responds quickly and performs well in avoiding collisions when applied to path planning for the rock drilling manipulator.


Learning‐Based Rapid Phase‐Aberration Correction and Control for Robot‐Assisted MRI‐Guided Low‐/High‐Intensity Focused Ultrasound Treatments

Magnetic resonance imaging (MRI)‐guided focused ultrasound (MRg‐FUS) is an effective and noninvasive procedure for treating diseases such as neurological disorders. Phase adjustment on ultrasound transducers can only achieve a limited focal‐spot steering range. When treating large abdominopelvic targets, mechanical adjustment on the transducers' position and orientation is the prerequisite for enlarging the steering range. Therefore, we previously designed an MRI‐guided robot to manipulate the transducers to offer sufficient focal‐spot movement range. This could provide more modulation solutions to constructive ultrasound interference. However, full‐wave ultrasound propagation inside a patient's heterogeneous abdominal media is complex and nonlinear, posing significant challenges in ultrasound modulation and beam motion control. Here, we propose a novel learning‐based phase‐aberration correction and model‐free control framework for robot‐assisted MRg‐FUS treatments. The correction policy guarantees rapid aberration compensation within 5.0 ms. Submillimeter refocusing accuracy is achieved in both the liver (0.32 mm) and pancreas (0.51 mm), meeting clinical requirements for focal targeting. Our controller can accommodate nonlinear phase actuation with fast convergence (< 5.7 ms) and ensure accurate positional tracking with a mean error of 0.26 mm, without prior knowledge of inhomogeneous media. Compared with the conventional model‐based method, it contributes to 61.77%–70.39% mean error reduction without requiring model parameter tuning.


Development of an Omnidirectional Mobile Passive‐Compliant Magnetic‐Wheeled Wall‐Climbing Robot for Variable Curvature Facades

Wall‐climbing robots are increasingly being used to inspect and maintain large ship facades, ensuring structural safety and reliability. However, conventional rigid robots often struggle with adaptability and flexibility on complex curved surfaces. To address this, we propose an omnidirectional magnetic‐wheel wall‐climbing robot with a passive‐compliant suspension system. This design allows all magnetic wheels to adhere simultaneously to inclined surfaces with varying curvatures, and each wheel can independently rotate to any angle. We quantitatively analyzed the relationship between configuration parameters and the spatial position mapping of the robot on complex elevations to verify its adaptability to variable curvatures. Based on normalized surface configurations of varying curvatures on ship facades, we establish the robot's kinematic transformation flow. We develop spatial dynamic models for three motion modes on variable‐curvature surfaces using energy conservation principles, analyzing driving‐wheel motion constraints and friction‐type differences across the modes to enable precise calculation of robot motion parameters. The proposed robot enhances ship facade maintenance by enabling stable, flexible motion on variable‐curvature surfaces, improving efficiency, safety, and adaptability.


Resilient Timed Elastic Band Planner for Collision‐Free Navigation in Unknown Environments

June 2025

·

17 Reads

·

1 Citation

In autonomous navigation, trajectory replanning, refinement, and control command generation are essential for effective motion planning. This paper presents a resilient approach to trajectory replanning addressing scenarios where the initial planner's solution becomes infeasible. The proposed method incorporates a hybrid A* algorithm to generate feasible trajectories when the primary planner fails and applies a soft constraints‐based smoothing technique to refine these trajectories, ensuring continuity, obstacle avoidance, and kinematic feasibility. Obstacle constraints are modeled using a dynamic Voronoi map to improve navigation through narrow passages. This approach enhances the consistency of trajectory planning, speeds up convergence, and meets real‐time computational requirements. In environments with around 30% or higher obstacle density, the ratio of free space before and after placing new obstacles, the RESILIENT TIMED ELASTIC BAND (RTEB) planner achieves approximately 20% reduction in traverse distance, traverse time, and control effort compared to the timed elastic band (TEB) planner and nonlinear model predictive control (NMPC) planner. These improvements demonstrate the RTEB planner's potential for application in field robotics, particularly in agricultural and industrial environments, where efficient and resilient navigation is crucial.


Mechanism Design and Performance Analysis of Multi‐Road Screw‐Propelled Vehicle Based on DEM–MBD Coupling

Screw‐propelled vehicle (SPV) is a novel multi‐terrain vehicle that demonstrates significant potential in military, rescue, and extreme environment applications due to its exceptional terrain adaptability and maneuverability. However, most existing studies primarily focus on performance analysis in a single environment, resulting in a lack of systematic research on vehicle performance across multiple road conditions. In this study, an innovative coupling method combining multi‐body dynamics (MBD) and the discrete element method (DEM) was employed to establish a comprehensive model that captures the interaction between the SPV and complex terrain. This model accurately simulates the mechanical behavior of the vehicle under various challenging road conditions, including sand, snow, and hay fields. Using the response surface method (RSM) and the Monte‐Carlo method, we optimized key structural parameters of the SPV, such as the height‐to‐diameter ratio, spiral angle, and number of blades. This optimization process identified the parameter combinations that yield the best performance across multiple road conditions. Experimental results indicate that the adaptability and stability of the optimized SPV in diverse environments have significantly improved, thereby validating the accuracy and reliability of the numerical model. This study provides a solid theoretical foundation for enhancing and optimizing the performance of future SPV and is expected to facilitate ongoing advancements in screw propulsion technology for complex tasks and extreme conditions.


VTOL Air Vehicle With Fixed‐Inclined Rotors and a Rudder Vane

This paper describes a vertical take off and landing (VTOL) aircraft equipped with a rotor obliquely fixed to the wing and a control surface that changes the direction of the slipstream of the propeller. Conventional VTOL aircraft, such as lift‐cruise or tilt rotor, show either increased drag and weight, resulting in reduced efficiency and payload capacity, or added mechanical complexity accompanied by sophisticated control requirements. Unlike other conventional VTOL aircraft, this vehicle achieves a stable transition between fixed‐wing and rotary‐wing modes simply by changing the pitch attitude of the aircraft. As the rotor is mounted at an inclined angle, it can control the pitch not only during hovering but also during horizontal flight by using differential thrust between the front and rear propulsion. Moreover, the roll angle can be controlled by using differential thrusts between the left and right thrusts. Additionally, this aircraft achieves yaw axis control by changing the direction of the rotor's slipstream. The control surface that adjusts the direction of the slipstream is termed the “rudder vane,” which is expected to provide rapid yaw response during hovering and naturally enhance directional stability during horizontal flight. Overall, this design promises improved energy efficiency, reduced mechanical and software complexity, and enhanced maneuverability, making the vehicle particularly well suited to demanding real‐world operational environments. In this paper, mathematical modeling of a fixed‐tilt rotor VTOL aircraft equipped with a rudder vane is performed, and a control law for the aircraft is designed and validated via flight tests.


High Stability Traversing Practice of a MAS‐UGV on Impassable Abrupt Roads

Multi‐axle active suspension vehicles are very promising for traversing impassable abrupt roads under high payload demands and complement the strengths of mobile robots. However, this hope is severely blocked by the high‐order indeterminate property of the vehicle and the complex vehicle‐ground interactions, making the suspension adjustment infinitely solvable. For the low‐speed traversing reality, this paper first proposes a body attitude and wheel load coupling control model based on the explicit characterization of the load‐deformation coupling nature of vehicles; then, the suspension adjustment‐based wheel gait control is designed for typical impassable scenarios, wherein the coupling control model is invoked to solve the suspension adjustment under the stability objectives; finally, a multi‐axle active suspension unmanned ground vehicle (MAS‐UGV) in near‐conventional configurations is developed and typical abrupt road traversing experiments are carried out. Experiments confirm that the proposed framework and controller can support high stability traversing of multi‐axle active suspension vehicles (at least 50% improvement in attitude stability and controllable wheel loads) on originally impassible abrupt roads via the bionic‐like gait, thus providing new possibilities for UGVs and even near‐conventional vehicles to construct versatile, tough terrain crossing schemes.


Visual‐Inertial SLAM for Unstructured Outdoor Environments: Benchmarking the Benefits and Computational Costs of Loop Closing

May 2025

·

11 Reads

Simultaneous localization and mapping (SLAM) is essential for mobile robotics, enabling autonomous navigation in dynamic, unstructured outdoor environments without relying on external positioning systems. These environments pose significant challenges due to variable lighting, weather conditions, and complex terrain. Visual‐Inertial SLAM has emerged as a promising solution for robust localization under such conditions. This paper benchmarks several open‐source visual‐Inertial SLAM systems, including traditional methods (ORB‐SLAM3, VINS‐Fusion, OpenVINS, Kimera, and SVO Pro) and learning‐based approaches (HFNet‐SLAM, AirSLAM), to evaluate their performance in unstructured natural outdoor settings. We focus on the impact of loop closing on localization accuracy and computational demands, providing a comprehensive analysis of these systems' effectiveness in real‐world environments and especially their application to embedded systems in outdoor robotics. Our contributions further include an assessment of varying frame rates on localization accuracy and computational load. The findings highlight the importance of loop closing in improving localization accuracy while managing computational resources efficiently, offering valuable insights for optimizing Visual‐Inertial SLAM systems for practical outdoor applications in mobile robotics. The data set and the benchmark code are available under https://github.com/iis-esslingen/vi-slam_lc_benchmark.


Improved Robot Localization and Mapping Using Adaptive Tuna Schooling Optimization With Sensor Fusion Techniques

Localization in mobile robotics is essential for achieving autonomy. Effective localization systems integrate data from multiple sensors to enhance state estimation and achieve accurate positioning. Accurate real‐time localization is crucial for robot control and trajectory following. Key challenges include initializing the inertial measurement unit (IMU) biases and the direction of gravity, as well as determining the metric scale with a monocular camera. Traditional visual–inertial (VI) initialization techniques rely on precise vision‐only motion assessments to address these issues. Multi‐sensor fusion faces challenges, such as precise calibration, initialization of sensor groups, and handling measurement errors with varying rates and delays. This paper introduces an Adaptive Tuna Schooling Optimization (ATSO) method to adjust localization strategies based on environmental conditions dynamically. The environmental factors affecting the localization process are considered in the optimization algorithm, and the position is optimally selected accordingly. Using Q‐learning with the Q‐DNN performs the decision‐making process based on past experiences. The dynamic adaptation of the weight parameter allows the algorithm to converge toward optimal solutions, reducing computational complexity. Experimental results demonstrate that the proposed approach improves localization performance, even in challenging conditions.


A Study Demonstrating That Using Gravitational Offset to Prepare Extraterrestrial Mobility Missions Is Misleading

May 2025

·

79 Reads

Recently, there has been a surge of international interest in extraterrestrial exploration targeting the Moon, Mars, the moons of Mars, and various asteroids. This contribution discusses how current state‐of‐the‐art Earth‐based testing for designing rovers and landers for these missions currently leads to overly optimistic conclusions about the behavior of these devices upon deployment on the targeted celestial bodies. The key misconception is that gravitational offset is necessary during the terramechanics testing of rover and lander prototypes on Earth. The body of evidence supporting our argument is tied to a small number of studies conducted during parabolic flights and insights derived from newly revised scaling laws. We argue that what has prevented the community from fully diagnosing the problem at hand is the absence of effective physics‐based models capable of simulating terramechanics under low‐gravity conditions. We developed such a physics‐based simulator and utilized it to gauge the mobility of early prototypes of the Volatiles Investigating Polar Exploration Rover. This contribution discusses the results generated by this simulator, how they correlate with physical test results from the NASA‐Glenn SLOPE lab, and the fallacy of the gravitational offset in rover and lander testing. The simulator, which is open‐source and publicly available, also supports studies for in situ resource utilization activities, for example, digging, bulldozing, and berming, in low‐gravity environments.


Comparison of DSO and ORB‐SLAM3 in Low‐Light Environments With Auxiliary Lighting and Deep Learning Based Image Enhancing

In the evolving landscape of robotic navigation, the demand for solutions capable of operating in challenging scenarios, such as low‐light environments, is increasing. This study investigates the performance of two state‐of‐the‐art (SOTA) visual simultaneous localization and mapping (VSLAM) algorithms, direct sparse odometry (DSO) and ORBSLAM3, in their monocular implementation, in the dark indoor scenarios where the only light source is provided by an auxiliary light system installed on a robot. A modified Pioneer3‐DX robot, equipped with a monocular camera, LED bars, and a lux meter, is utilized to collect a novel data set, “LUCID—Lighting Up Campus Indoor Spaces Data Set,” in real‐world, low‐light indoor environments. The data set includes image sequences enhanced using a generative adversarial network (GAN) to simulate varying levels of image enhancement. Through comprehensive experiments, we assess the performances of the V‐SLAM algorithm, considering the critical balance between maintaining adequate auxiliary illumination and enhancing. This study provides insights into the optimization of robotic navigation in lowlight conditions, paving the way for more robust and reliable autonomous navigation systems.


Design, Development, Integration and Field Evaluation of a Dual Robotic Arm Mango Harvesting Robot

To solve the problems of high labor intensity and high cost when picking mango manually, a mango picking robot system with dual robotic arms was developed to realize automatic mango picking. Firstly, the YOLOMS network was used to realize the 3D localization of picking points for single mangoes and mango clusters in unstructured environments. Secondly, a new “shearing and grasping integrated” end‐effector for non‐destructive harvesting of mangoes was designed. Then, a task division method for the workspace of the dual robotic arm harvesting robot was proposed to minimize the likelihood of collisions between dual arms. Additionally, a depth‐first picking strategy was introduced to reduce fruit damage and enhance the success rates of picking mangoes from layered canopies. Finally, a mango harvesting robotic system with dual arms was developed and integrated. The performance of the system was evaluated by field mango picking experiments. The results showed that the average recognition rate and planning success rate of the harvesting robot were 83.94% and 98.45%, respectively. In addition, the average harvesting success rate of the robot was 73.92%, and the average single‐fruit harvesting time was 8.93 s. Compared with the robot with single arm, the harvesting time was reduced by 48.38%, which indicated that the harvesting efficiency of the dual robotic arm harvesting robot was significantly improved. The average collision‐free harvesting rate with the addition of the depth‐first harvesting strategy was 91.68%, which verified the rationality and effectiveness of the dual robotic arm collaborative mango harvesting robotic system. The results provide technical support for automated mango harvesting.


A Novel Review on Quadruped Robots Design Variants, Gait Modulation, and Motion Planning Schemes

May 2025

·

67 Reads

Quadruped robots are gaining more importance among researchers due to their adaptability to complex terrains, though their stability handling is complex. Quadruped robots are one of the best kinds of legged robotic systems with regard to their framework and movement flexibility. For making quadrupeds fully autonomous, it is important to concentrate on their modeling, modulation, and maneuverability. This article sheds light on quadruped robots, starting from the early‐stage developments of TITAN series quadrupeds to current progress based on variations of design, gait analysis, control, and motion planning, so as to provide directions for future researchers to develop efficient quadrupeds. Furthermore, we have made a comparative analysis on various aspects, including various mobile robots, material specifications, leg structure and topology, crucial modeling parameters, sensors and actuation systems, as well as traditional and advanced algorithms. This work explores gait analysis, followed by numerous researchers concentrating on various gait stability challenges; in addition, it presents the studies on control strategies of quadruped robots based on a PID controller, neural network controller, fuzzy logic controller, delayed feedback controller, hybrid controller, and other peculiar controllers. Furthermore, the representative explorations on motion planning algorithms of quadruped robots have been done. To conclude, this paper provides an overview of the various variants of quadrupeds, focusing on important aspects, followed by an analysis of pivot features and providing solutions to current challenges and issues so as to help future researchers in the field identify key areas of research.


Design and Analysis of New Obstacle Avoidance Scheme With Dimensionality Reduction for Motion Planning of Redundant Robot Manipulators

May 2025

·

4 Reads

Obstacle avoidance (OA) is an important issue in the motion planning of redundant robot manipulators. Various effective OA schemes have been reported, but they may suffer from a large amount of calculation for the situation of multiple obstacles and/or complex‐shaped obstacles. In this paper, to address the aforementioned limitation, a new OA scheme with dimensionality reduction is proposed and studied for redundant robot manipulators. Specifically, by combining robot kinematics and geometry, a typical inequality criterion for OA is designed, which can reduce the calculation for an obstacle point from the general three dimensions to one dimension. Such an inequality criterion is further aided by (1) the dynamic selection for the situation of a large number of obstacle points, and (2) the feature extraction for the situation of complex‐shaped obstacles. With the OA environment optimized and the obstacles' dimension limited, the computational efficiency of generating the inequality criterion for specific scenarios can thus be improved. By incorporating the inequality criterion and the joint physical constraint, the new dimensionality‐reduction OA (DROA) scheme is developed for redundant robot manipulators. Such a DROA scheme is depicted as a quadratic program that is solved by the reinforcement learning method. Simulation and experiment results under the PA10 robot manipulator verify the efficacy and applicability of the proposed DROA scheme.


Research on Steering Path Tracking Performance of Articulated Quad‐Tracked Vehicle Based on Fuzzy PID Control

May 2025

·

7 Reads

The articulated quad‐track vehicles exhibit excellent mobility and obstacle‐crossing capabilities in outdoor environments, making them widely applicable in agriculture and military fields. Their steering control is a complex issue influenced by numerous factors. To reduce the computational complexity of the controller, achieve rapid system response, and simultaneously improve the stability and precision of the articulated quad‐track vehicles during the steering control process, an optimal matching analysis is performed between the inner and outer track speed ratios and the deflection angles at the front and rear articulation points of the vehicle. By utilizing fuzzy proportional–integral–derivative control and visual navigation, a path‐tracking control experimental platform for the articulated quad‐track vehicle is designed. Through a combination of virtual prototype simulations and physical experiments, the distance deviation and heading angle deviation between the actual driving path of the virtual and experimental prototypes and the preset path are analyzed. The designed path–tracking control system can adjust the driving speeds of the left and right tracks and the articulation point deflection angle based on the preset driving path, enabling the vehicle to track the path. Under stable steering conditions, the distance deviation is within 0.1 m, and the heading angle deviation is within 6°, demonstrating excellent control performance.


Design and Analysis of Double‐Ring Robotic Coconut Tree Climber for Enhanced Performance

May 2025

·

6 Reads

In the dynamic field of agricultural technology, the development of coconut tree climbers exemplifies significant progress in addressing the challenges of efficient and safe coconut harvesting. Designing an unmanned coconut tree climber robot is complex due to the unpredictable structures of the coconut tree trunk and crown. Key challenges include developing a climbing mechanism, ensuring smooth ascents and descents, managing payload stability, and designing an effective harvester for coconut bunches, all of which impact the robot's overall performance. This paper introduces a novel design featuring a double‐ring structure for the climber robot, aimed at enhancing its performance. The study includes a comprehensive static analysis to determine the average range of torque values for the actuators. Dynamic and kinematic analyses are conducted to establish essential relationships that predict the robot's characteristics before testing. A four‐degree‐of‐freedom manipulator is used as the harvester. The proposed methodology was tested on a coconut tree trunk in a lab setup and field conditions across 10 different coconut trees. Real‐time data collected during these tests were validated against predictions made through simulations before experimentation. The analyses, including theoretical analysis, simulation outcomes, and experimental test setups, conclusively demonstrate that the proposed structure maintains consistent stability throughout the climbing process, even on trees with varying inclinations and trunk radii relative to height. The success rates of the double‐ring setup consistently surpass those of the single‐ring configuration, with success rates ranging from 80% to 100% for the single ring and 100% for the double‐ring setup.


Air‐to‐Ground Target Detection and Tracking Based on Dual‐Stream Fusion of Unmanned Aerial Vehicle

May 2025

·

4 Reads

Both visible and infrared images are important sources of intelligence information on the battlefield, and air‐to‐ground reconnaissance by UAV is an important means to obtain intelligence. However, there are great challenges in ground target detection and tracking, especially in complex battlefield environments. Aiming at the problem of insufficient accuracy of target detection by a single type of sensor in the battlefield environment at this stage, a target detection method by fusion of visible and infrared images is proposed in this paper, which is called ReconnaissanceFusion‐YOLO (RF‐YOLO), and with the help of infrared imagery, it can effectively improve the accuracy of target detection in the case of insufficient light. The performance of target detection in the battlefield is significantly improved by introducing two key innovative modules: dual feature fusion (DFF) module and feature fusion corrector (FFC) module. The DFF module enhances multi‐channel feature fusion through a novel concatenation and channel‐wise attention mechanism, while the FFC module performs feature correction between parallel streams using spatial and channel‐wise weights, addressing noise and uncertainty in different modalities. These modules are integrated on top of a dual‐stream YOLO architecture, allowing for effective fusion of visible and infrared information. RF‐YOLO was trained and evaluated using the FLIR data set, containing 5142 pairs of strictly aligned visible and infrared images. Results demonstrate that RF‐YOLO significantly outperforms benchmark networks in terms of robustness requirements. Specifically, the large model of RF‐YOLO achieves an mAP of 0.831, which is a significant improvement compared to the YOLOv5l inf benchmark's 0.739. This represents an improvement of over 12% in detection accuracy. Additionally, RF‐YOLO offers a Nano version that balances accuracy and speed. The Nano version achieves an mAP of 0.765, while maintaining a model size of only 11.5 MB, making it suitable for deployment on UAV edge computing devices with limited resources. To validate the practical applicability of our approach, this paper successfully implements target detection and tracking on a real UAV's edge computing device using the ROS system and SiameseRPN, combined with the proposed RF‐YOLO. Real‐world flight tests were conducted on an internal playground, demonstrating the effectiveness of our method in actual UAV applications. The system achieved a processing rate of approximately 10 fps at 640 × 640 resolution on an NVIDIA TX2 edge computing device, showcasing its real‐time performance capability in practical scenarios. This study contributes to enhancing UAV‐based battlefield reconnaissance capabilities by improving the accuracy and robustness of target detection and tracking in complex environments. The proposed RF‐YOLO method, along with its successful implementation on a real UAV platform, provides a promising solution for advanced military intelligence gathering and decision‐making support.


PR2: A Physics‐ and Photo‐Realistic Humanoid Testbed With Pilot Study in Competition

May 2025

·

2 Reads

This paper presents the development of a P hysics‐ r ealistic and P hoto‐ r ealistic humanoid robot testbed, PR2, to facilitate collaborative research between Embodied Artificial Intelligence (Embodied AI) and robotics. PR2 offers high‐quality scene rendering and robot dynamic simulation, enabling (i) the creation of diverse scenes using various digital assets, (ii) the integration of advanced perception or foundation models, and (iii) the implementation of planning and control algorithms for dynamic humanoid robot behaviors based on environmental feedback. The beta version of PR2 has been deployed for the simulation track of a nationwide full‐size humanoid robot competition for college students, attracting 137 teams and over 400 participants within 4 months. This competition covered traditional tasks in bipedal walking, as well as novel challenges in loco‐manipulation and language‐instruction‐based object search, marking a first for public college robotics competitions. A retrospective analysis of the competition suggests that future events should emphasize the integration of locomotion with manipulation and perception. By making the PR2 testbed publicly available at https://github.com/pr2-humanoid/PR2-Platform , we aim to further advance education and training in humanoid robotics. Video demonstration: https://pr2-humanoid.github.io/ .


Predictive Obstacle Avoidance Algorithm for Under‐Actuated Unmanned Surface Vehicle Under Disturbances via Reinforcement Learning

May 2025

·

13 Reads

Due to the growing complexity of diverse maritime tasks, underactuated unmanned surface vehicle (USV) has become a research hotspot. The rapid development of deep reinforcement learning (DRL) technology has brought forth a novel approach for the USV autonomous control, rendering unnecessary the dynamical modeling of the target USV. To further improve the USV collision avoidance performance against maritime disturbances, this paper presents a predictive reinforcement learning method for USV obstacle avoidance control. A prediction module is designed to generate latent features that depict environmental states. After that, the prediction feature is provided for a DRL‐based policy module to produce an action distribution for the underactuated unmanned surface vehicle. The proposed method in this paper can enable the USV avoid obstacle and reach the destination solely based on its local observational information, without relying on prior global information. Simulation and physical experiments have demonstrated that, compared to general DRL methods, the proposed method exhibits stronger robustness to environmental disturbances, enabling the USV to reach the destination while avoid the obstacle.


Slip‐Compensation‐Based Path Tracking Control for Tracked Robots Using VBEKF and Backstepping Control

May 2025

·

1 Read

Tracked robots are widely used in agriculture, military, mining, and other fields. During the traveling process of tracked robots, the complex interaction between the tracks and the ground causes slip, which leads to problems such as low path tracking accuracy and poor control stability. To solve this thorny problem, quantitative control compensation parameters are generally obtained through experiments, or extended Kalman filter (EKF) is designed based on Gaussian noise to estimate slip parameters during motion. However, the sensor measurement noise of tracked robots usually exhibits a non‐Gaussian distribution in uneven terrain and variable soil conditions. Under such circumstances, these methods exhibit larger errors and demonstrate inadequate adaptability. Therefore, this paper proposes a variational Bayesian EKF (VBEKF) algorithm for slip parameters estimation, and designs a slip compensation path tracking controller to improve the accuracy and adaptability of the control system of tracked robots under complex operating conditions. The main contributions of this paper are as follows: (1) The non‐Gaussian noise was re‐modeled using the Student's t‐distribution, and combined with variational Bayesian, the VBEKF algorithm was designed. This algorithm can more accurately estimate the slip parameters between the tracks and soil under complex and varying operating conditions, demonstrating enhanced adaptability. (2) Based on the backstepping control principle, a path tracking controller with slip parameter compensation was designed for tracked robots. This controller dynamically adjusts its output control based on the estimated slip parameters to eliminate the impact of slip between the tracks and soil on path tracking accuracy. Finally, the effectiveness of the method was demonstrated through simulations and experiments. This study can improve the adaptability and stability of tracked robots under complex and variable operating conditions, ensuring accurate and rapid task completion, and has broad application prospects.


Advances and Trends in Terrain Classification Methods for Off‐Road Perception

May 2025

·

20 Reads

Off‐road autonomous vehicles (OAVs) are becoming increasingly popular for navigating challenging environments in agriculture, military, and exploration applications. These vehicles face unique challenges, such as unpredictable terrain, dynamic obstacles, and varying environmental conditions. Therefore, it is essential to have an efficient terrain classification system to ensure safe and efficient operation of OAVs. This paper provides an overview of recent advances and emerging trends in off‐road terrain classification methods. Through a comprehensive literature review, this study explores the use of sensor modalities and techniques that leverage both appearance and geometry of the terrain for classification tasks. The study discusses learning‐based approaches, particularly deep learning, and highlights the integration of multiple sensor modalities through hybrid multimodal techniques. Finally, this study reviews the available off‐road datasets and explores the use cases and applications of terrain classification across various autonomous domains. Given the rapid advancements in terrain classification, this paper organizes and surveys to provide a comprehensive overview. By offering a structured review of the current landscape, this paper significantly enhances our understanding of terrain classification in unstructured environments, while also highlighting important areas for future research, particularly in deep‐learning‐based advancements.


Practical Predefined‐Time Tracking Control of 6‐DOF Autonomous Vehicles With Input Quantization and Saturation

May 2025

·

12 Reads

Trajectory tracking control is a fundamental problem in the control of unmanned systems. In practical systems, actuators often have input quantization and saturation constraints, and failing to account for these constraints can affect control convergence time, precision, and even lead to system instability. Therefore, designing a practical predefined time controller specifically for unmanned systems with input quantization and saturation is particularly important. In this study, a novel practical predefined‐time control criterion and predefined‐time control criterion are proposed. A novel observer with predefined‐time convergence is designed which can deal with both input quantization and input saturation. It is efficient without high computational cost, local optima, or complex parameter tuning. It can deal with ship systems with 6 degrees of freedom exposed to external disturbance. The 6 degrees of freedom model provides a more comprehensive representation of the dynamic characteristics. An autonomous vehicle model is used for testing, and the effectiveness of the proposed algorithm has been demonstrated.


Multiple Population Genetic Algorithm‐Based Inverse Kinematics Solution for a 6‐DOF Manipulator

May 2025

·

7 Reads

Compared to traditional fixed configuration manipulators, modular manipulators occupy less space, offer greater flexibility, and demonstrate stronger adaptability to diverse environments. These characteristics make them particularly suitable for operating in unknown environments, such as disaster rescue and pipeline inspection. This paper presents the design of a modular robotic arm and proposes a novel approach to solving the inverse kinematics problem for a 6‐DOF (degree of freedom) tandem manipulator using a Multi‐population Genetic Algorithm (MPGA). The proposed method overcomes the high nonlinearity and computational complexity of traditional genetic algorithms (SGA) by incorporating real‐number encoding, Exponential Ranking Selection, and a combination of Simple and Gaussian mutations. These improvements significantly enhance the algorithm's convergence speed, accuracy, and robustness, making it suitable for complex robotic systems. The manipulator's forward kinematics is established using the Denavit‐Hartenberg (D‐H) method, and the MPGA optimizes the inverse kinematics solution. Simulations and experiments on both fixed and mobile platforms demonstrate the MPGA's superior performance in terms of computational efficiency and solution accuracy. The manipulator accurately followed the planned trajectory, validating the method's effectiveness. This study provides a novel and efficient solution for inverse kinematics in high‐DOF manipulators, offering potential applications across various robotic systems.


Design and Control of a Hexapod Robot RENS H3 for Lateral Walking on Unknown Rugged Terrains

May 2025

·

8 Reads

Legged robots provide an efficient alternative for navigation in complex terrains. However, few studies have explored dynamic locomotion for hexapod robots navigating unknown, rugged terrains. In this paper, the design, control, and implementation of a hexapod robot, RENS H3, inspired by the lateral movement of crabs, are presented with a focus on its adaptability in unknown, uneven terrains. The robot's structural design is introduced, and a hardware control framework for hexapod robots is developed. Additionally, a hierarchical control framework based on model predictive control is proposed, integrating terrain‐adaptive control and foot‐end Cartesian space force compensation based on posture adjustment into the control architecture to enhance the robot's robustness and terrain adaptability on slopes and unstructured terrains. The proposed method's robustness, adaptability, and energy efficiency were demonstrated through a series of experiments conducted on various outdoor slope terrains, unstructured terrains, and the multi‐terrain testbed. Comparative experimental tests further validated the advantages of the approach in unknown rugged terrains.


Adaptive Deep Reinforcement Learning Hybrid Neuro‐Fuzzy Inference System Based Path Planning Algorithm for Mobile Robot

May 2025

·

17 Reads

Mobile robot route planning is the process of calculating a mobile robot's collision‐free path from a starting place to a goal point surrounded by its environment. It is a critical component of mobile robotics since it enables robots to move around and perform tasks independently in a variety of conditions. The Global Positioning System (GPS), the Adaptive Neuro‐Fuzzy Inference System (ANFIS), and deep reinforcement learning (DRL) are commonly used tools for tracking as well as control. This paper proposes a GPS‐based DRL‐ANFIS navigation method for mobile robots that avoid collisions. The GPS‐based controller keeps the robot on track to achieve its global and flexible objective. Next, a fuzzy inference system (FIS) is employed to simulate obstacle avoidance using fuzzy linguistics on distance sensor data. In addition, a mobile robot path planning technique based on enhanced DRL is proposed to address the issues of limited exploration capability and sparse reward of environmental state space in mobile robot route planning in unfamiliar environments. Finally, the proposed ANFIS parameters are fine‐tuned using a tent‐based artificial hummingbird algorithm (AHA) to attain the desired location. The proposed approach evaluates the results using MATLAB. The simulation study is designed to assess the proposed strategy's effectiveness in navigating a mobile robot across a complex environment, as well as its performance in comparison to existing collision‐free navigation systems. As a result, the proposed approach takes a shorter path and avoids barriers to get the robot closer to its destination. The proposed approach has a computation time of 22 s and a path planning efficiency of 96.56%, which is 5.56% higher than the traditional DRL model.


Journal metrics


4.2 (2023)

Journal Impact Factor™


22%

Acceptance rate


15.0 (2023)

CiteScore™


26 days

Submission to first decision


3.156 (2023)

SNIP


$3,590.00 / £2,380.00 / €3,010.00

Article processing charge

Editors