Research Area
Getting there safely and fast - planning and control for agile vehicles, from racing cars to spacecraft in proximity operations
The Motion Planning and Control research area develops advanced algorithms for enabling autonomous systems to navigate safely and efficiently through complex environments. Our work spans from theoretical foundations in computational geometry and optimization to practical implementations in autonomous vehicles, aerial robots, and space systems.
Core research includes sampling-based planning methods, optimization-based trajectory generation, learning-enhanced planning, reinforcement learning for navigation, and advanced control techniques for agile maneuvers. We develop real-time planning algorithms with formal guarantees, robust planning under uncertainty, and hierarchical planning that integrates high-level decision-making with low-level control.
Our work enables autonomous driving, drone navigation, high-speed vehicle control, robotic manipulation, space proximity operations, and human-robot collaboration. We develop open-source planning and control libraries with high-performance implementations, visualization tools, and integration with standard robot and vehicle middleware.
This project addresses path planning for autonomous vehicles in traffic using reinforcement learning and deep inverse reinforcement learning to model interactions and learn expert driving behaviors
ARCHES develops distributed planning algorithms for heterogeneous autonomous swarms by using multi-resolution graphs and bounded rationality models to enable efficient coordination in complex environments
Wavelets, beamlets and adaptive multiscale grids used as a common tool for two problems: encoding paths efficiently enough to plan on embedded hardware with limited resources, and solving optimal and nonlinear control problems numerically
This project develops incremental sampling-based motion planning algorithms and stochastic optimal control methods on random graphs to address computational bottlenecks in high-dimensional autonomous systems
This project combines randomized graph representations with stochastic optimal control to accelerate sampling-based motion planning and to make it robust to motion, sensing and model uncertainty in high-dimensional spaces
We develop new control methodologies for vehicle stability and handling that mimic expert human driver reactions during emergency maneuvers to improve active safety systems
NASCAR develops perception and planning algorithms to achieve agile autonomous vehicle response by mimicking the cognitive and reflexive strategies of expert human race drivers
This project develops intelligent flight guidance and planning systems to assist pilots in making optimal decisions during on-board emergencies
This research enhances automotive active safety systems by introducing learning and adaptation to customize assistance based on driver behavior and skills
This project develops intelligent control algorithms for high-speed autonomous ground vehicles operating in hostile off-road environments, incorporating controlled slipping and sliding
Tsiotras, P. and Sanz-Diaz, R., “Real-Time Near-Optimal Feedback Control of Aggressive Vehicle Maneuvers,” in Optimization and Optimal Control in Automotive Systems, Eds: H. Waschl, I. Kolmanovky, M. Steinbuch and L. del Re, Springer Lecture Notes in Control and Information Sciences, Vol. 455, March 2014, pp. 109-129.
Velenis, E., Frazzoli, E., and Tsiotras P., “Steady-State Cornering Equilibria and Stabilization for a Vehicle During Extreme Operating Conditions,” International Journal of Vehicle Autonomous Systems, Special Issue on Autonomous and Semi-Autonomous Control for Safe Driving of Ground Vehicles, Vol.8, Nos. 2-4, pp. 217-241, 2010.
Velenis, E., Katzourakis, D., Frazolli, E., Tsiotras, P. and Happee, R., “Stabilization of Steady-State Drifting for a RWD Vehicle,” 10th International Symposium on Advanced Vehicle Control (AVEC), Loughborough, UK, August 22- 26, 2010.
Cowlagi, R. and Tsiotras, P., “Beyond Quadtrees: Cell Decompositions for Path Planning using Wavelet Transforms,” 46th IEEE Conference on Decision and Control, New Orleans, LA, Dec. 12-14, 2007, pp. 1392-1397.
C. Canudas-de-Wit, P. Tsiotras, X. Claeys, J. Yi, and R. Horowitz, “Friction Tire/Road Modeling, Estimation and Optimal Braking Control,” in Nonlinear and Hybrid Systems in Automotive Control, Eds: Rolf Johansson and Anders Rantzer, Lecture Notes in Control and Information Science, Springer-Verlag, London, October 2002, pp. 165-229.