Conference Paper

A Method to use Nonlinear Dynamics in a Whisker Sensor for Terrain Identification by Mobile Robots

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... For contact-sensor-based schemes, IMU [9] or tactile sensors [10] are investigated by using the direct contact information of the ground properties through application of convolutional neural network (CNN) methods. Inspired by animals such as rats and sea lions which use whiskers to navigate in the dark and perceive environmental information and features without vision [11], artificial whiskers sensors have been designed and constructed for robot navigation [12], terrain identification [13], object detection [14], size measurement [15], shape recognition [16], and surface information identification [17]. ...
Article
Full-text available
In this letter, we present for the first time the use of tapered whisker-based reservoir computing (TWRC) system mounted on a mobile robot for terrain classification and roughness estimation of unknown terrain. Hall effect sensors captured the oscillations at different locations along a tapered spring that served as a reservoir to map time-domain vibrations signals caused by the interaction perturbations from the ground to frequency domain features directly. Three hall sensors are used to measure the whisker reservoir outputs and these temporal signals could be processed efficiently by the proposed TWRC system which can provide morphological computation power for data processing and reduce the model training cost compared to the convolutional neural network (CNN) approaches. To predict the unknown terrain properties, an extended TWRC method including a novel detector is proposed based on the Mahalanobis distance in the Eigen space, which has been experimentally demonstrated to be feasible and sufficiently accurate. We achieved a prediction success rate of 94.3\% for six terrain surface classification experiments and 88.7\% for roughness estimation of the unknown terrain surface.
Article
Identifying terrain type is important for safely operating robots exploration in unstructured environments. In this letter, we firstly proposed a novel tapered whisker-based semi-supervised reservoir computing (TWSSRC) system for improving terrain classification and terrain property estimation for traversability assessment with low computing cost. Three Hall sensors are used to capture the vibration at different locations of the tapered whisker. It could provide morphological computation power to achieve frequency separation in the time domain simultaneously without any data procession and only with the help of an additional simple linear regression, different signals can be classified. The movement of the robot on different types of terrain will result in different vibration behaviors of the whiskers and the whiskered robot can learn from prior physical experiences through cost-efficient self-supervised reservoir computing to achieve auto-labeling of new terrain and terrain classification. Experimental results demonstrate that this method can achieve good performance when the robot encounters new terrain and can accurately estimate the property of the unknown terrain surface at different robot speeds.
Article
Full-text available
Mammals like rats, who live in dark burrows, heavily depend on tactile perception obtained through the vibrissal system to move through gaps and to discriminate textures. The organization of a mammalian whisker follicle contains multiple sensory receptors and glands strategically organized to capture tactile sensory stimuli of different frequencies. In this paper, we used a controllable stiffness soft robotic follicle to test the hypothesis that the multimodal sensory receptors together with the controllable stiffness tissues in the whisker follicle form a physical structure to maximize tactile information. In our design, the ring sinus and ringwulst of a biological follicle are represented by a linear actuator connected to a stiffness controllable mechanism in-between two different frequency-dependent data capturing modules. In this paper, we show for the first time the effect of the interplay between the stiffness and the speed of whisking on maximizing a difference metric for texture classification.
Conference Paper
Full-text available
Nowadays, it is notorious the increasing use of autonomous vehicles in different outdoor field applications such as agriculture, the mining industry, environmental monitoring, among others. In this context, the determination of the traversability level of a terrain is a fundamental task for safe and efficient navigation of Autonomous Ground Vehicles(AGVs) in unstructured unknown outdoor environments. Information like roughness of the ground is important when velocity control and other dynamic issues are concerned. However, most of the techniques in the literature use camera or lidar sensors to evaluate the ground around the robot, leading to complex and high cost systems. More simpler methods use only inertial sensors to estimate the roughness properties of the terrain, however they can be very sensitive to the robot’s speed. In this paper, we propose a novel classifier capable of cluster different terrains based only on acceleration data provided by an Inertial Measurement Unit (IMU). We demonstrate with real-world experiments that, for different forward velocities, the mean accuracy of the classification exceeds 80%. Our method also incorporates a controller to regulate the speed according to the terrain identified by the robot in order to avoid abrupt movements over terrain changes. (PDF) Speed-invariant terrain roughness classification and control based on inertial sensors. Available from: https://www.researchgate.net/publication/321892371_Speed-invariant_terrain_roughness_classification_and_control_based_on_inertial_sensors [accessed Feb 12 2020].
Article
Full-text available
Terrain classification is a critical component of any autonomous mobile robot system operating in unknown real-world environments. Over the years, several proprioceptive terrain classification techniques have been introduced to increase robustness or act as a fallback for traditional vision based approaches. However, they lack widespread adaptation due to various factors that include inadequate accuracy, robustness and slow run-times. In this paper, we use vehicle-terrain interaction sounds as a proprioceptive modality and propose a deep long-short term memory based recurrent model that captures both the spatial and temporal dynamics of such a problem, thereby overcoming these past limitations. Our model consists of a new convolution neural network architecture that learns deep spatial features, complemented with long-short term memory units that learn complex temporal dynamics. Experiments on two extensive datasets collected with different microphones on various indoor and outdoor terrains demonstrate state-of-the-art performance compared to existing techniques. We additionally evaluate the performance in adverse acoustic conditions with high-ambient noise and propose a noise-aware training scheme that enables learning of more generalizable models that are essential for robust real-world deployments.
Article
Full-text available
Soft machines have recently gained prominence due to their inherent softness and the resulting safety and resilience in applications. However, these machines also have disadvantages, as they respond with complex body dynamics when stimulated. These dynamics exhibit a variety of properties, including nonlinearity, memory, and potentially infinitely many degrees of freedom, which are often difficult to control. Here, we demonstrate that these seemingly undesirable properties can in fact be assets that can be exploited for real-time computation. Using body dynamics generated from a soft silicone arm, we show that they can be employed to emulate desired nonlinear dynamical systems. First, by using benchmark tasks, we demonstrate that the nonlinearity and memory within the body dynamics can increase the computational performance. Second, we characterize our system's computational capability by comparing its task performance with a standard machine learning technique and identify its range of validity and limitation. Our results suggest that soft bodies are not only impressive in their deformability and flexibility but can also be potentially used as computational resources on top and for free.
Article
Full-text available
High visual acuity allows parallel processing of distant environmental features, but only when photons are abundant enough. Diurnal tiger beetles (Carabidae: Cicindelinae) have acute vision for insects and visually pursue prey in open, flat habitats. Their fast running speed causes motion blur that degrades visual contrast, forces stop-and-go pursuit and potentially impairs obstacle detection. We demonstrate here that vision is insufficient for obstacle detection during running, and show instead that antennal touch is both necessary and sufficient for obstacle detection. While running, tiger beetle vision appears to be photon-limited in a way reminiscent of animals in low-light habitats. Such animals often acquire wide-field spatial information through mechanosensation mediated by longer, more mobile appendages. We show that a nocturnal tiger beetle species waves its antennae in elliptical patterns typical of poorly sighted insects. While antennae of diurnal species are also used for mechanosensation, they are rigidly held forward with the tips close to the substrate. This enables timely detection of path obstructions followed by an increase in body pitch to avoid collision. Our results demonstrate adaptive mechanosensory augmentation of blurred visual information during fast locomotion, and suggest that future studies may reveal non-visual sensory compensation in other fast-moving animals.
Article
Full-text available
Several recent studies have investigated the problem of object feature extraction with artificial whiskers. Many of these studies have used an approach in which the whisker is rotated against the object through a small angle. Each small-angle “tap” of the whisker provides information about the radial distance between the base of the whisker and the object. By tapping at various points on the object, a full representation of the surface can be gradually constructed in three-dimensional space. It is clear, however, that this tapping method does not exploit useful information about object contours that could be extracted by “sweeping” the whisker against the object. Rotating the whisker against the object through a large angle permits the collection of a sequence of contact points as the whisker slips along the surface. The present paper derives an algorithm based on a numerical cantilever beam model of the whisker to measure object profile shape over a single large-angle whisker rotation using only information about torque and angle at the whisker base. The algorithm is validated experimentally using three different object shapes. As the method does not require measurement of force, it is well suited for implementation on an array of robotic whiskers to accomplish quick and precise object feature extraction.
Conference Paper
Full-text available
Whiskers are powerful sensors for robots that are not only useful for basic tasks such as obstacle avoidance, but also have the potential for gathering rich information about objects. We have developed an active multi-whisker array modeled on the rat whisker system which can be amounted on a mobile robot. We show that with this whisker array we can discriminate different textures based on the frequencies elicited by the whiskers. We exploit the phase-locked structure of our data using sensory-motor integration. Two factors enable better discrimination of the textures: firstly, considering several touch events from one whisker; and secondly, combining the information from more than one whisker.
Article
Full-text available
This paper proposes a new active sensor system (active antenna) that can detect not only the contact location between an insensitive flexible beam and an environment but also the information of the environment's surface where the beam makes contact. The active antenna is simply composed of a flexible beam, actuators to move the beam, position sensors to measure the rotational angle of the beam, and a moment sensor. We first show that the contact distance under no lateral slip is proportional to the rotational compliance that the beam can sense at the rotational center. The lateral slip, which possibly occurs according to the pushing direction and the environment's geometry, overestimates the rotational compliance, and as a result, brings a large sensing error for the localizing contact point. The goal of this paper is to find the contact location under such conditions. We explore how to detect a lateral slip and how to determine the new pushing direction to avoid it. We show an algorithm that can search for the pushing direction which can avoid any lateral slip. The convergence of this algorithm is shown and a practical utilization of this algorithm is also discussed with a trade-off between the number of trials and the sensing accuracy
Article
Full-text available
In this paper we present the current implementation of the artificial mouse (AMouse), a robot based on a Khepera platform with two active artificial whisker arrays and an omnidirectional camera. This robot has been designed in close cooperation with biologists and neuroscientists to serve as a tool for studying biological models of rodent behavior. Furthermore, the interplay between different sensory modalities - visual and somatosensory - can be investigated. An important somatosensory organ are whiskers. Whiskers are versatile sensors for short-range navigation and exploration that are widespread in many animal species, especially in rodents. Rats for example can use them for local navigation, for exploration of objects (3) and for discrimination of different surface textures (6).
Article
Understanding the fundamental relationships between physics and its information-processing capability has been an active research topic for many years. Physical reservoir computing is a recently introduced framework that allows one to exploit the complex dynamics of physical systems as information-processing devices. This framework is particularly suited for edge computing devices, in which information processing is incorporated at the edge (e.g. into sensors) in a decentralized manner to reduce the adaptation delay caused by data transmission overhead. This paper aims to illustrate the potentials of the framework using examples from soft robotics and to provide a concise overview focusing on the basic motivations for introducing it, which stem from a number of fields, including machine learning, nonlinear dynamical systems, biological science, materials science, and physics.
Chapter
The problem of tactile object identification has a strong connection with the problem of Simultaneous Localization and Mapping (SLAM) in a physical 6-dimensional environment. Here we introduce our preliminary results describing the performance of our RatSLAM-inspired 6D SLAM algorithm dubbed Whisker-RatSLAM, which is used to map and localize a whisker-array relative to the surface of an object. We show that our approach can successfully localize using the physical and simulation data sets taken from an active array of artificial whiskers as they explore a range of household objects. We also demonstrate the ability of Whisker-RatSLAM to be used for object identification.
Article
Almost all mammals use their mystacial vibrissae (whiskers) as important tactile sensors. There are no sensors along the length of a whisker: All sensing is performed by mechanoreceptors at the whisker base. To use artificial whiskers as a sensing tool in robotics, it is essential to be able to determine the three-dimensional (3D) location at which a whisker has made contact with an object. With the assumption of quasistatic, frictionless, single-point contact, previous work demonstrated that the 3D contact point can be uniquely determined if all six components of force and moment are measured at the whisker base, but these measurements require a six-axis load cell. Here, we perform simulations to investigate the extent to which each of the 20 possible "triplet" combinations of the six mechanical signals at the whisker base uniquely determine 3D contact point location. We perform this analysis for four different whisker profiles (shapes): Tapered with and without intrinsic curvature, and cylindrical with and without intrinsic curvature. We show that whisker profile has a strong influence on the particular triplet(s) of signals that uniquely map to the 3D contact point. The triplet of bending moment, bending moment direction, and axial force produces unique mappings for tapered whiskers. Four different mappings are unique for a cylindrical whisker without intrinsic curvature, but only when large deflections are excluded. These results inform the neuroscience of vibrissotactile sensing and represent an important step toward the development of artificial whiskers for robotic applications.
Article
The stress response of cantilever beam to non-Gaussian random base excitation isinvestigated based on Monte-Carlo simulation. First, the statistical properties and spectralcharacteristics of non-Gaussian random vibrations are analyzed qualitatively; and the conclusionis that spectral method based on power spectrum density (PSD) is not applicable for non-Gaussianrandom vibrations. Second, the stress response formula of cantilever beam under non-Gaussianrandom base excitations is established in the time-domain, and the factors influencing the outputkurtosis are subsequently determined. Two numerical examples representing different practicalsituations are analyzed in detail. The discrepancies of the stress responses to Gaussian, steadynon-Gaussian and burst non-Gaussian base excitations are analyzed in terms of root mean square(RMS), kurtosis and fatigue damage. The transmissibility of RMS and high-kurtosis of steadynon-Gaussian random base excitation is different from that of burst non-Gaussian case. Finally,the fatigue life corresponding to every base excitation is calculated using the rainflow method inconjunction with the Palmgren-Miner rule. Finite element analysis is also carried out forvalidation. The predicted fatigue lives corresponding to Gaussian, steady non-Gaussian and burstnon-Gaussian base excitations are compared quantitatively. Finally, in the fatigue damage pointof view, the discrepancies among the three kinds of random base excitations are summarized.
Article
The ability to safely navigate is a crucial prerequisite for truly autonomous systems. A robot has to distinguish obstacles from traversable ground. Failing on this task can cause great damage or restrict the robots movement unnecessarily. Due to the security relevance of this problem, great effort is typically spent to design models for individual robots and sensors, and the complexity of such models is correlated to the complexity of the environment and the capabilities of the robot. We present a semi supervised learning approach, where the robot learns its traversability capabilities from a human operating it. From this partially and only positive labeled training data, our approach infers a model for the traversability analysis, thereby requiring very little manual effort for the human. In practical experiments we show that our method can be used for robots that need to reliably navigate on dirt roads as well as for robots that have very restricted traversability capabilities.
Article
This article presents novel techniques for real-time terrain characterization and assessment of terrain traversability for a field mobile robot using a vision system and artificial neural networks. The key terrain traversability characteristics are identified as roughness, slope, discontinuity, and hardness. These characteristics are extracted from imagery data obtained from cameras mounted on the robot and are represented in a fuzzy logic framework using perceptual, linguistic fuzzy sets. The approach adopted is highly robust and tolerant to imprecision and uncertainty inherent in sensing and perception of natural environments. The four traversability characteristics are combined to form a single Fuzzy Traversability Index, which quantifies the ease-of-traversal of the terrain by the mobile robot. Experimental results are presented to demonstrate the capability of the proposed approach for classification of different terrain segments based on their traversability. © 2001 John Wiley & Sons, Inc.
Article
This article summarizes some of the key features of the rat vibrissal system, including the actively controlled sweeping movements of the vibrissae known as whisking, and reviews the past and ongoing research aimed at replicating some of this functionality in biomimetic robots.
Article
We investigated the transduction operation and function of the mystacial vibrissae, using a comparative morphological analysis and behavioral experiments in rats. Vibrissal architecture was documented in a series of mammals to identify evolutionary conserved features of vibrissal organization. As a result of this analysis, we distinguish between a frontal microvibrissal system and macrovibrissal system of the mystacial pad. The latter was invariably comprised of whiskers aligned in regular rows. In each row, whiskers were oriented perpendicular to the animal's rostrocaudal axis; all shared a specific dorsoventral orientation. In all species, progressing from rostral to caudal in any vibrissal row, there was a precisely exponential increase in whisker length. Each whisker appeared to act as a lever-like transducer, providing information as to whether or not--but not where--an individual vibrissa had been deflected. The rat's frontal microvibrissae system was found to have a vibrissa tip density that was about 40 times higher than that of the mystacial macrovibrissae. In behavioral studies spatial tasks and object recognition tasks were used to investigate (a) search behaviors; (b) single whisker movements; (c) object recognition ability; and (d) effects of selective macro- or microvibrissae removal on task performances. A clear distinction between the functional roles of macro- and microvibrissae was demonstrated in these studies. Mystacial macrovibrissae were critically involved in spatial tasks, but were not essential for object recognition. Microvibrissae were critically involved in object recognition tasks, but were not essential for spatial tasks. A synthesis of these morphological and behavioral data led to the following functional concept: The mystacial macrovibrissae row is a distance decoder. Its function is to derive head centered obstacle/opening contours at the various dorsoventral angles represented by vibrissal rows. This distance detector model is functionally very different from traditional concepts of whisker function, in which the mystacial whiskers were hypothesized to form a fine grain skin-like object-recognizing tactile surface.