The Parkour Cars project aims to develop high fidelity real-time systems for perception, planning and control of agile vehicles in challenging terrain including jumps and loop-the-loops. My current research is focused on the local planning and control problem. Due to the difficulty of the maneuvers, the planning and control systems must consider the underlying physical model of the vehicle and terrain. This style of simulation-in-the-loop planning enables very accurate prediction and correction of the vehicle state, as well as the ability to learn precise attributes of the underlying physical model.
The planning and control system is examined in a motion capture laboratory with numerous ramps and jumps. To facilitate the accurate physical simulation, the laboratory and ramp surfaces are scanned using a RGB-D fusion system to provide holistic 3D meshes for use in physical simulation.
The test vehicle orientation is captured using the motion capture system and subsequently fused in a sliding window filter with IMU measurements obtained from the vehicle to obtain a high-fidelity pose estimate which is used in the planner. This fusion system serves to compliment the motion capture state estimate with high speed IMU measurements as well as provide temporary state predictions if the vehicle moves outside of motion-capture coverage.
Nima Keivan, Steven Lovegrove, and Gabe Sibley, “A Holistic Framework for Planning, Real-time Control and Model Learning for High-speed Ground Vehicle Navigation Over Rough 3D Terrain”, IROS 2012 Workshop on Robot Motion Planning: Online, Reactive, and in Real-time [.pdf]
Nima Keivan and Gabe Sibley, “Realtime Simulation-in-the-loop Control for Agile Ground Vehicles”, TAROS 2014 (Best Student Paper) [.pdf]