Risk-Aware Kinodynamic Motion Planning Under Uncertainty For Safe Navigation on Planetary Environments
2026-08-11 • Robotics
Robotics
AI summaryⓘ
The authors address how robots exploring space can plan safe and efficient paths, even when they aren’t sure about the terrain or their sensors. They first use a special planning method (AO-RRT) to find a path that considers risks and robot movement limits. Then, they improve this path using another technique (sequential convex programming) to make it as good as possible. By measuring risk carefully with a method called CVaR, their approach significantly reduces the chances of problems during robot movement. They tested this idea in simulations and real robots with great success.
autonomous space explorationmotion planningAO-RRTsequential convex programmingrisk-aware planningconditional value-at-riskkinodynamic planningrobot perceptionterrain mechanicssampling-based planner
Authors
Sachin Sunil Kelkar, Tanmay Dokania, Yashwanth Kumar Nakka
Abstract
For autonomous space exploration, robotic agents need to perform motion planning in which environmental interactions may be unknown. Learning these interactions, such as terrain mechanics for wheeled robots, can introduce uncertainties that lead to risky motion plans and potentially hazardous operations or mission failures. Moreover, uncertainties induced by perception-based systems can exacerbate the problem of safe motion planning. In this letter, we address the problem of performing cost-optimal kinodynamic motion planning with risk awareness. We approach this in two steps. First, a sampling-based planner (AO-RRT) generates a dynamically feasible, risk-aware, and asymptotically cost-optimal trajectory. Second, we formulate motion planning as a nonlinear optimization problem and solve it using sequential convex programming (SCP), using the AO-RRT trajectory as an initial solution. By quantifying risk using conditional value-at-risk (CVaR), we demonstrate a reduction in risk by over $\sim$97\% across trajectories in simulation and hardware experiments.