John-David Yoder

Probabilistic Analysis of Dynamic Scenes and Collision Risks Assessment to Improve Driving Safety

The article deals with the analysis and interpretation of dynamic scenes typical of urban driving. The key objective is to assess risks of collision for the ego-vehicle. We describe our concept and methods, which we have integrated and tested on our experimental platform on a Lexus car and a driving simulator. The on-board sensors deliver visual, telemetric and inertial data for environment monitoring. The sensor fusion uses our Bayesian Occupancy Filter for a spatio-temporal grid representation of the traffic scene. The underlying probabilistic approach is capable of dealing with uncertainties when modeling the environment as well as detecting and tracking dynamic objects. The collision risks are estimated as stochastic variables and are predicted for a short period ahead with the use of Hidden Markov Models and Gaussian processes. The software implementation takes advantage of our methods, which allow for parallel computation. Our tests have proven the relevance and feasibility of our approach for improving the safety of car driving.

Initial results in the development of a guidance system for a powered wheelchair

This paper describes the development of an automatically guided powered wheelchair for individuals with severe disabilities. The navigation and control of the wheelchair is based the accurate estimation of the location of the wheelchair within its operating workspace. A novel method used to generate and track reference paths which take the user to and from various destinations within the wheelchairs environment is presented. The paper also provides a qualitative description of the restrictions and requirements that are specific to the wheelchair application as well as the way in which the current system addresses these restrictions and requirements. Finally, actual experimental runs of the wheelchair system are presented.

Automatic visual guidance of a forklift engaging a pallet

This paper presents the development of a prototype vision-guided forklift system for the automatic engagement of pallets. The system is controlled using the visual guidance method of mobile camera-space manipulation, which is capable of achieving a high level of precision in positioning and orienting mobile manipulator robots without relying on camera calibration. The paper contains development of the method, the development of a prototype forklift as well as experimental results in actual pallet engagement tasks. The technology could be added to AGV systems enabling them to engage arbitrarily located pallets. It also could be added to standard forklifts as an operator assist capability.

High-precision visual control of mobile manipulators

In this paper, we present a high-precision visual control method for mobile manipulators called mobile camera-space manipulation (MCSM). Development of MCSM was inspired by the unique challenges presented in conducting unmanned planetary exploration using rovers. In order to increase the efficacy of such missions, the amount of human interaction must be minimized due to the large time delay and high cost of transmissions between Earth and other planets. Using MCSM, the rover can maneuver itself into position, engage a target rock, and perform any of a variety of manipulation tasks all with one round-trip transmission of instruction. MCSM also achieves a high level of precision in positioning the onboard manipulator relative to its target. Experimental results are presented in which a rover positions a tool mounted in its manipulator to within 1 mm of the desired target feature on a rock. MCSM makes efficient use of all of the systems degrees of freedom (DOF), which reduces the required number of actuators for the manipulator. This reduction in manipulator DOFs decreases overall system weight, power consumption, and complexity while increasing reliability. MCSM does not rely on a calibrated camera system. Its excellent positioning precision is robust to model errors and uncertainties in measurements, a great strength for systems operating in harsh environments.

A Visibility-Based Approach for Occupancy Grid Computation in Disparity Space

Occupancy grids are a very convenient tool for environment representation in robotics. This paper will detail a novel approach for computing occupancy grids from stereo vision and show its application to intelligent vehicles. In the proposed approach, occupancy is initially computed directly in the stereoscopic sensors disparity space. The calculation formally accounts for the detection of obstacles and road pixels in disparity space, as well as partial occlusions in the scene. In the second stage, this disparity-space occupancy grid is transformed into a Cartesian space occupancy grid to be used by subsequent applications. This transformation includes spatial and temporal filtering. The proposed method is designed to easily be processed in parallel. Consequently, we chose to implement it on a graphics processing unit, which allows real-time processing for demanding applications. In this paper, we present this method, and we propose an application to the problem of perception in a road environment. Results are presented with real road data, qualitatively comparing this approach with other methods.

Using the disparity space to compute occupancy grids from stereo-vision

The occupancy grid is a popular tool for probabilistic robotics, used for a variety of applications. Such grids are typically based on data from range sensors (e.g. laser, ultrasound), and the computation process is well known [1]. The use of stereo-vision in this framework is less common, and typically treats the stereo sensor as a distance sensor, or fails to account for the uncertainties specific to vision. In this paper, we propose a novel approach to compute occupancy grids from stereo-vision, for the purpose of intelligent vehicles. Occupancy is initially computed directly in the stereoscopic sensors disparity space, using the sensors pixel-wise precision during the computation process and allowing the handling of occlusions in the observed area. It is also computationally efficient, since it uses the u-disparity approach to avoid processing a large point cloud. In a second stage, this disparity-space occupancy is transformed into a Cartesian space occupancy grid to be used by subsequent applications. In this paper, we present the method and show results obtained with real road data, comparing this approach with others.

Automatic Pallet Engagment by a Vision Guided Forklift

This paper presents a vision-guided control method called mobile camera-space manipulation (MCSM) that enables a robotic forklift vehicle to engage pallets based on a pallet’s actual current location by using feedback from vision sensors that are part of the robotic forklift. MCSM is capable of high precision mobile manipulation control without relying on strict camera calibration. The paper contains development of the method as well as experimental results with a forklift prototype in actual pallet engagement tasks. The technology could be added to AGV (automatically guided vehicle) systems enabling them to engage arbitrarily located pallets. It also could be added to standard forklifts as an operator assist capability.

Teachless teach-repeat: Toward vision-based programming of industrial robots

Modern programming of industrial robots is often based on the teach-repeat paradigm: a human operator places the robot in many key positions, for teaching its task. Then the robot can repeat a path defined by these key positions. This paper proposes a vision-based approach for the automation of the teach stage. The approach relies on a constant auto-calibration of the system. Therefore, the only requirement is a precise geometrical description of the part to process. The realism of the approach is demonstrated through the emulation of a glue application process with an industrial robot. Results in terms of precision are very promising.

Experiments in Vision-Laser Fusion Using the Bayesian Occupancy Filter

Occupancy Grids have been used to represent the environment for some time. More recently, the Bayesian Occupancy Filter (BOF), which provides both an estimate of likelihood of occupancy of each cell, AND a probabilistic estimate of the velocity of each cell in the grid, has been introduced and patented. This work presents the first experiments in the use of the BOF to fuse data obtained from stereo vision and multiple laser sensors, on an intelligent vehicle platform. The paper describes the experimental platform, the approach to sensor fusion, and shows results from data captured in real traffic situations.

Experiments Comparing Precision of Stereo-Vision Approaches for Control of an Industrial Manipulator

Despite years of research in the area of robotics, the vast majority of industrial robots are still used in “teach-repeat” mode. This requires that the workpiece be in exactly the same position and orientation every time. In many high-volume robotics applications, this is not a problem, since the parts are likely to be fixtured anyway. However, in small to medium lot applications, this can be a significant limitation. The motivation for this project was a corporation who wanted to explore the use of visual control of a manipulator to allow for automated teaching of robot tasks for parts that are run in small lot sizes.