Welcome to the Autonomous Systems Laboratory
The autonomous systems lab (ASL) develops algorithms and control methods for autonomous systems operating in uncertain environments. Systems include autonomous ground and aerial vehicles, multi-robot systems, autonomous driving, and robots that interact with humans.
The following are some current areas of focus:
- Robot motion planning: methods for planning robot motion to efficiently complete complex tasks.
- Learning planning policies: learning robot behaviors and policies through repeated task executions.
- Planning under uncertainty: planning and sensing for operation in unknown environments.
- Persistent monitoring and scene reconstruction: monitoring and building real-time maps for complex 3D environments.
- Future transportation systems: coordinating and dispatching vehicles for ride-sharing and urban transportation.
- Active preference learning: coordinating robots to work with humans in task specification and collaborative assembly.
- Distributed and submodular optimization: collective decision making strategies for objectives that exhibit diminishing returns.
- Autonomous driving: Generating safe and efficient motion in real-world environments.
- Other areas of interest include dynamic vehicle routing, informative path planning, task allocation, formation control, consensus/rendezvous and ocean sampling.
- Oct. 7, 2020
Nils Wilde and Armin Sadeghi both completed their PhD degrees! Congratulations!
- June 1, 2020
Ahmad Bilal Asghar completed his PhD in May 2020 and is now a postdoctoral fellow at the University of Toronto in the Space & Terrestrial Autonomous Robotic Systems (STARS) Laboratory.
- Apr. 29, 2020
Our results on Improving user specifications for robot behavior through active preference learning: Framework and evaluation have appeared in the International Journal of Robotics Research (IJRR). The preprint is available on arXiv.