Joshua Marshall

• Doctor of Philosophy
• Professor (Full) at Queen's University

This paper introduces two-dimensional axis mapping, which estimates axis maps (AMs) based on LiDAR measurements. An AM describes the dominant orientations of surfaces in an environment and is void of positional information. As a consequence of the directional nature of the map, there are significant differences compared with traditional mapping alg...

This chapter presents an overview of the state of the art in mining robotics, from surface to underground applications, and beyond. Mining is the practice of extracting resources for utilitarian purposes. Today, the international business of mining is a heavily mechanized industry that exploits the use of large diesel and electric equipment. These...

Although passive sensors are widely used for many mobile robotics applications that perform mapping and localization functions, there are many environments (e.g., mining and planetary) where active sensors are more practical. However, at present, most 3D SLAM algorithms that do use LiDAR and/or time-of-flight (ToF) sensors exploit only range and be...

This paper describes a dataset collected along a 1 km section of beach near Katwijk, The Netherlands, which was populated with a collection of artificial rocks of varying sizes to emulate known rock size densities at current and potential Mars landing sites. First, a fixed-wing unmanned aerial vehicle collected georeferenced images of the entire ar...

This paper presents the development and field validation of an iterative learning-based admittance control algorithm for autonomous excavation in fragmented rock using robotic wheel loaders. An admittance control strategy is augmented with iterative learning, which automatically updates control parameters based on the error between a target bucket...

Reinforcement learning (RL) has gained traction for its success in solving complex tasks for robotic applications. However, its deployment on physical robots remains challenging due to safety risks and the comparatively high costs of training. To avoid these problems, RL agents are often trained on simulators, which introduces a new problem related...

This paper proposes the Real-Time Fast Marching Tree (RT-FMT), a real-time planning algorithm that features local and global path generation, multiple-query planning, and dynamic obstacle avoidance. During the search, RT-FMT quickly looks for the global solution and, in the meantime, generates local paths that can be used by the robot to start exec...

This paper proposes the Real-Time Fast MarchingTree (RT-FMT), a real-time planning algorithm that featureslocal and global path generation, multiple-query planning,and dynamic obstacle avoidance. During the search, RT-FMTquickly looks for the global solution and, in the meantime,generates local paths that can be used by the robot to startexecution...

This paper proposes a high‐performance path following algorithm that combines Gaussian processes (GP) based learning and feedback linearization (FBL) with model predictive control (MPC) for ground mobile robots operating in off‐road terrains, referred to as GP‐FBLMPC. The algorithm uses a nominal kinematic model and learns unmodeled dynamics as GP...

With recent advances in mobile robotics, autonomous systems, and artificial intelligence, there is a growing expectation that robots are able to solve complex problems. Many of these problems require multiple robots working cooperatively in a multi-robot system. Complex tasks may also include the interconnection of task-level specifications with ro...

The number of available tools for dynamic simulation of robots has been growing rapidly in recent years. However, to the best of our knowledge, there are very few reported quantitative comparisons of the most widely-used robot simulation tools. This article attempts to partly fill this gap by providing quantitative and objective comparisons of four...

3D hand pose estimation (HPE) is the process of locating the joints of the hand in 3D from any visual input. HPE has recently received an increased amount of attention due to its key role in a variety of human-computer interaction applications. Recent HPE methods have demonstrated the advantages of employing videos or multi-view images, allowing fo...

Human-machine interaction using remote hand gestures is becoming increasingly prevalent across various industries. However, their potential application to heavy construction equipment is often overlooked. This article presents a robust and inexpensive hand gesture recognition system that was implemented and tested on a robotic 1-tonne wheel loader....

Hand pose estimation (HPE) can be used for a variety of human-computer interaction applications such as gesture-based control for physical or virtual/augmented reality devices. Recent works have shown that videos or multi-view images carry rich information regarding the hand, allowing for the development of more robust HPE systems. In this paper, w...

Hand pose estimation (HPE) can be used for a variety of human-computer interaction applications such as gesture-based control for physical or virtual/augmented reality devices. Recent works have shown that videos or multi-view images carry rich information regarding the hand, allowing for the development of more robust HPE systems. In this paper, w...

A novel formulation called Virtual Interest Point is presented and used to register point clouds. An implicit quadric surface representation is first used to model the point cloud segments. Macaulay’s resultant then provides the intersection of three such quadrics, which forms a virtual interest point (VIP). A unique feature descriptor for each VIP...

Joshua A. Marshall, The robot revolution is here: How it's changing jobs and businesses in Canada, In The Conversation, February 23, 2021, Online: https://theconversation.com/the-robot-revolution-is-here-how-its-changing-jobs-and-businesses-in-canada-155267.

The ability of robotic excavators to acquire meaningful knowledge about materials during digging can augment their autonomous functionality, as well as optimize downstream operations in construction and mining. Some material properties, such as rock sizes, can be determined visually, but these methods cannot see what lies beneath. In this work, a c...

This paper presents the conceptual design, construction, and preliminary testing of a novel auto-rotating platform for cavity surveying. Cavity surveying involves generating a 3D model of an opening from acquired point cloud data. 3D models are used for volume estimation, stope reconciliation, dilution control, convergence monitoring, and rock mass...

Fully immersive Virtual Reality (VR) has the ability to take students to remote locations or allow them to interact with a simulated environment without having to leave campus. This study investigated whether VR is an effective tool to help students increase their knowledge and understanding of various engineering programs and as a result increase...

This paper describes the design, industrial application, and field testing of a technique for autonomous wheeled‐vehicle path following that uses iterative learning control (ILC) in a feedback linearized space. One advantage of this approach is that ILC is used without having to employ approximate linearization at every time step. The main contribu...

Ventilation system analysis for underground mines has remained mostly unchanged since the Atkinson method was made popular by McElroy in 1935. Data available to ventilation technicians and engineers is typically limited to the quantity of air moving through any given heading. Because computer-aided modelling, simulation, and ventilation system desi...

This paper investigates the extension of an admittance control scheme toward learning and adaptation of its setpoints to achieve controllable bucket fill factor for robotic excavation of fragmented rock. A previously developed Dig Admittance Controller (DAC) is deployed on a 14-tonne capacity robotic load-haul-dump (LHD) machine, and full-scale exc...

This paper introduces three-dimensional axis mapping (3DAM), a new method for joint orientation estimation that rapidly collects data from a mobile platform containing a scannerless LiDAR and an inertial measurement unit (IMU). The mobile platform is moved through the environment either as a handheld device or by mounting it to a remotely operated...

This paper describes the design, tuning, and extensive field testing of an admittance-based autonomous loading controller (ALC) for robotic excavation. Several iterations of the ALC were tuned and tested in fragmented rock piles-similar to those found in operating mines-by using both a robotic 1-tonne capacity Kubota R520S diesel-hydraulic surface...

Traffic management in underground mines, especially on production ramps, is a difficult problem to optimize and control. Most operations use one of a few common policies; e.g., the so-called “lock-out” and “loaded-vehicle-priority” policies. The work presented in this paper uses discrete-event simulation to study the efficiency of multiple policies...

This paper introduces the LiDAR compass, a bounded and extremely lightweight heading estimation technique that combines a two-dimensional laser scanner and axis maps, which represent the orientations of flat surfaces in the environment. Although suitable for a variety of indoor and outdoor environments, the LiDAR compass is especially useful for em...

In this paper we describe field trials of an admittance-based Autonomous Loading Controller (ALC) applied to a robotic Load-Haul-Dump (LHD) machine at an underground mine near Örebro, Sweden. The ALC was tuned and field tested by using a 14-tonne capacity Atlas Copco ST14 LHD mining machine in piles of fragmented rock, similar to those found in ope...

A new method is presented for robustly and efficiently registering two noisy point clouds. The registration is driven by establishing correspondences of virtual interest points, which do not exist in the original point cloud data, and redefined by the intersection of parametric surfaces extracted from the data. Parametric surfaces, such as planes,...

Ramps (or declines) are often used in underground mines to transport ore, waste, materials, and personnel. This paper studies mine ramp productivity and presents results from a set of computer simulations designed to model the fundamental behaviours of ramp haulage systems. Simulations show that, under fundamental assumptions without random disturb...

This paper presents a solution to part of the problem of making robotic or semi-robotic digging equipment less dependant on human supervision. A method is described for identifying rocks of a certain size that may affect digging efficiency or require special handling. The process involves three main steps. First, by using range and intensity data f...

Cigar Lake is a high-grade uranium deposit, located in northern Saskatchewan, Canada. In order to extract the uranium ore remotely, thus ensuring minimal radiation dose to workers and also to access the ore from stable ground, the Jet Boring System (JBS) was developed by Cameco Corporation. This system uses a high-powered water jet to remotely exca...

Autonomous science augments the capabilities of planetary rovers by shifting the identification and selection of science targets from remote operators to the rover itself. This shift frees the rover from wasteful idle time and allows for more selective data collection. This paper presents an approach to autonomous science that is comprised of three...

This paper analyzes the dynamic traveling repairman problem (DTRP) considering desired properties for unmanned multi-agent systems. We analyze solutions for the DTRP contemplating three desired properties; systems using local sensing and communications, systems operable through disrupted communications, and systems robust to single-agent failures....

A practical localization technology for underground drift networks—such as those excavated in the practice of underground mining—has yet to become commercially available. This paper focuses on the problem of mapping GPS-deprived underground environments with the eventual goal of using these maps for navigation. Recent industry-directed work in the...

Localization using satellite-based GPS is not available in underground mines, therefore a new approach is required. This paper presents a method for localizing a sensor-equipped vehicle in a large-scale underground environment by using a particle filter and a collection of 2D a priori node maps. Sporadically placed passive RFID tags are used in the...

The high cost of planetary rover missions limits risk-taking and therefore restricts scientific exploration. Also, limited autonomy requires time-consuming manual commands that must be issued to the rover from a great distance. This pa per explores the combination of vision-based geological in formation inferred from a Bayesian Network (BN) with th...

The ability to determine the position and orientation of vehicles in real time is a key enabling technology for automation, traffic management, and to ensure safety in the presence of multiple operating vehicles. As explained in this paper, despite some misguided advertising within the mining community, a technology comparable to the satellite base...

The question of how to prescribe desired global behaviours for a system of interconnected agents through the application of only simple and local interactions has both theoretical and practical significance. In recent years, numerous papers have appeared in the control systems literature on the reconfiguration and stabilisation of multivehicle form...

Despite a proliferation of research in the area of mapping in the mobile robotics community, the practical realization of a truly useful and low-cost mapping technology for drift networks in underground mining has yet to become available. To this end, this paper presents recent industry-directed work in the development of a globally consistent occu...

Navigation and mapping are important subtasks in mobile robotics, particularly in large-scale passageway environments (e.g., in underground mines) where satellite GPS is not available. What makes robotic mapping in such environments especially challenging is the problem of identifying when the robot has returned to an already traversed area. This p...

Structure in the interconnection topology among individuals of a multiagent system plays a fundamental role in the system's steady-state and transient behaviors. This paper explores how certain interconnection topologies influence symmetry in a multiagent system's trajectories. It is shown how circulant connectivity preserves rotation, and in parti...

This paper presents the results and subsequent analysis of full-scale excavation experiments aimed at developing a practical understanding of how actuator forces evolve during excavation and how they relate to the interactions that occur between an excavator's end-effector and its environment. Our focus is on the excavation problem for fragmented r...

This paper describes the design, implementation, and field testing of an infrastructureless system for autonomous tramming (or hauling) of a center-articulated underground mining vehicle. Such vehicles are ubiquitous in underground mining, and effective automation of their tramming function has been a sought-after technology for more than a decade....

During the last decade, mining companies and mobile equipment manufacturers have pursued improved efficiency, productivity, and safety in underground mining operations by automating some of the functions of underground vehicles. This paper describes the implementation and successful field testing of a new infrastructureless guidance system for auto...

This paper describes the design, implementation, and field testing of an infrastructureless system for autonomous tramming (or hauling) of a centerarticulated underground mining vehicle. Described is the development of a fast, reliable, and robust “autotramming” technology that does not require the installation of fixed infrastructure throughout th...

Consequent to previously published theoretical work by Marshall, Broucke, and Francis, this paper summarizes the apparatus and results of multirobot coordination experiments conducted at the University of Toronto Institute for Aerospace Studies. These experiments successfully demonstrate the practicality of cyclic pursuit as a distributed control s...

In this paper, the stability of equilibrium formations for multiple unicycle systems in cyclic pursuit is studied in detail. The cyclic pursuit setup is particularly simple in that each unicycle i pursues only one other unicycle, unicycle i+1 (modulo n), where n is the number of unicycles. This research is principally motivated by the historical de...

This paper explores how the interconnection topology among individuals of a multiagent system influences symmetry in its trajectories. It is shown how circulant connectivity preserves cyclic group symmetries in a formation of simple planar integrators. Moreover, it is revealed to what extent circulant connectivity is necessary in order that symmetr...

Consequent to previously published theoretical work by Marshall, Broucke, and Francis, this paper summarizes the apparatus and results of multi-vehicle coordination experiments conducted at the University of Toronto Institute for Aerospace Studies. These experiments successfully demonstrated the practicality of cyclic pursuit as a distributed contr...

Inspired by the so-called "bugs" problem from mathematics, we study the geometric formations of multivehicle systems under cyclic pursuit. First, we introduce the notion of cyclic pursuit by examining a system of identical linear agents in the plane. This idea is then extended to a system of wheeled vehicles, each subject to a single nonholonomic c...

In this paper, we examine the problem of how to achieve certain geometric formations among a group of identical mobile autonomous agents. Our particular view is that the subject of cooperative control involves: multiple autonomous agents, such as wheeled robot vehicles; a locally shared information structure; a control strategy that is somehow dist...

Inspired by the so-called "bugs" problem from mathematics, we propose a cyclic pursuit strategy for multi-vehicle formations. A particular version of this pursuit problem is studied for a system of n wheeled vehicles, each subject to a single nonholonomic constraint, towards the achievement of certain trajectories in the plane. A full stability ana...

In this paper, we study the geometric formations of multi-vehicle systems under a control law based on cyclic pursuit. The pursuit framework is particularly simple in that, for n ordered and identical wheeled vehicles, vehicle i simply pursues vehicle i+1 modulo n. We show that, for unicycles with constant speed, the multi-vehicle system's equilibr...

Increased competition and recent globalization in the minerals industry has resulted in further demands for advanced mining equipment technology. The au-tonomous excavation problem for fragmented rock entails the design of a control sys-tem capable of regulating the complicated bucket-rock interactions that occur during excavation operations. A not...

In this paper, the stability of equilibrium formations for multiple unicycle systems in cyclic pursuit is studied in detail. The cyclic pursuit setup is particularly simple in that each unicycle i pursues only one other unicycle, unicycle i + 1 (modulo n), where n is the number of unicycles. This research is principally motivated by the historical...

In the pursuit of increased safety the mining industry has worked to develop systems for remote control and autonomous operation of both stationary and mobile equipment. This paper reports on a newly developed system for teleoperation and autonomous tramming of LHD (Load-Haul-Dump) mining vehicles that not only increases the safety of the operators...