Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper presents a sampling-based algorithm for integrated task and kinodynamic motion planning for robots operating under semantic uncertainty, where the robot must satisfy a Linear Temporal Logic over finite traces ($\ltlf$) specification. The problem is modeled as a Partially Observable Stochastic Hybrid System to capture robot dynamics, the $\ltlf$ task, and environmental uncertainty. The proposed anytime algorithm leverages the hybrid system structure, combining decision-making techniques with sampling-based motion planning, and is proven sound and asymptotically optimal.
Robots can now plan complex tasks with formal guarantees even when they don't know exactly what objects are where.
This paper tackles the problem of integrated task and kinodynamic motion planning in uncertain environments. We consider a robot with nonlinear dynamics tasked with a Linear Temporal Logic over finite traces ($\ltlf$) specification operating in a partially observable environment. Specifically, the uncertainty is in the semantic labels of the environment. We show how the problem can be modeled as a Partially Observable Stochastic Hybrid System that captures the robot dynamics, $\ltlf$ task, and uncertainty in the environment state variables. We propose an anytime algorithm that takes advantage of the structure of the hybrid system, and combines the effectiveness of decision-making techniques and sampling-based motion planning. We prove the soundness and asymptotic optimality of the algorithm. Results show the efficacy of our algorithm in uncertain environments, and that it consistently outperforms baseline methods.