Safe motion planning approach for noisy sensor measurement representation of the environment using a stochastic neural implicit representation and chance constrained optimization.
Task and Motion Planning framework that combines a SMT-based task planner, sampling-based motion planners and a novel optimization-based grounder to find optimal object placement locations and robot grasps for cluttered environments.
Human-in-the-loop algorithm to compute joint-space trajectories for high-DoF robots under partial observability
Optimization-based motion planning algorithm capable of incorporating sensing uncertainty for a variety of noise models
Review of optimization algorithms that can escape saddle points in Deep Learning and some experimental results