Problem
Research questions and friction points this paper is trying to address.
contingency planning
mobile robot navigation
safety constraint
reach-avoid problem
Hamilton-Jacobi reachability
SCRAMPPI: Efficient Contingency Planning for Mobile Robot Navigation via Hamilton-Jacobi Reachability
🤖 AI Summary
This work addresses the challenge of mission failure in mobile robots operating under sudden hazardous conditions due to inadequate emergency planning. The authors formulate emergency planning as a trajectory optimization problem subject to hard safety constraints and propose a novel framework that integrates Hamilton-Jacobi reachability analysis with a Model Predictive Path Integral (MPPI) sampling-based planner. By online computation of the value function associated with the backward reachable set, the method dynamically guides MPPI resampling to simultaneously generate nominal and emergency trajectories that satisfy safety constraints within a receding-horizon optimization scheme. This approach guarantees that the system can reach a safe set from any state at any time, substantially improving both sampling efficiency and safety. Experimental results demonstrate that the proposed framework effectively accomplishes adversarial obstacle avoidance tasks in both simulated and real-world robotic platforms.
📝 Abstract
Autonomous robots commonly aim to complete a nominal behavior while minimizing a cost; this leaves them vulnerable to failure or unplanned scenarios, where a backup or contingency plan to a safe set is needed to avoid a total mission failure. This is formalized as a trajectory optimization problem over the nominal cost with a safety constraint: from any point along the nominal plan, a feasible trajectory to a designated safe set must exist. Previous methods either relax this hard constraint, or use an expensive sampling-based strategy to optimize for this constraint. Instead, we formalize this requirement as a reach-avoid problem and leverage Hamilton-Jacobi (HJ) reachability analysis to certify contingency feasibility. By computing the value function of our safe-set's backward reachable set online as the environment is revealed and integrating it with a sampling based planner (MPPI) via resampling based rollouts, we guarantee satisfaction of the hard constraint while greatly increasing sampling efficiency. Finally, we present simulated and hardware experiments demonstrating our algorithm generating nominal and contingency plans in real time on a mobile robot in an adversarial evasion task.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Hamilton-Jacobi reachability
contingency planning
safe motion planning
MPPI
real-time navigation
🔎 Similar Papers
No similar papers found.
