Search Content

This report presents results of the research performed on the Autonomous Land Experimental Vehicle (ALX) at the University of Minnesota. ALX autonomously follows roadways through the use of visual perception, and executes obstacle detection and collision avoidance through the use of ultrasonic sonar range sensors. This report describes the ALX embedded real-time control system based on a multi-processor, multi-tasking architecture, and presents algorithms used for visual perception, path tracking, position estimation, obstacle detection, and collision avoidance. Computer simulation and experimental results also are presented.

This report summarizes research on a new collision avoidance strategy, the 'virtual bumper.' The research involves development and simulation testing of the virtual bumper, a two-dimensional control strategy that provides steering, throttle, and braking actuation to maneuver a vehicle in a dynamic environment with the goal of avoiding obstacles and other vehicles. The concept applies to both normal and emergency driving conditions. Under all circumstances, the virtual bumper incorporates vehicle dynamic limits to ensure that the control commands are within safe levels. The virtual bumper will attempt to avoid a collision and will, at least, minimize the magnitude of an unavoidable collision. To test the functionality of the virtual bumper, researchers evaluated several driving scenarios. The scenarios consider both normal driving situations and emergency driving conditions. The normal driving scenarios demonstrated that the control algorithm operates the vehicle similar to the way a human would. This is important because a comfortable and predictable (i.e., intuitive) system response is required for achieving driver acceptance. The emergency scenarios demonstrated that the strategy is capable of reacting appropriately while maintaining safe acceleration/deceleration levels for the vehicle. This evaluation showed that the virtual bumper can provide safe vehicle control for a broad range of driving situations.