Safe Navigation using Neural Radiance Fields via Reachable Sets
2026-04-29 • Robotics
Robotics
AI summaryⓘ
The authors focus on helping robots move safely in places full of obstacles by understanding what areas the robot can reach at any moment. They use a special technique called neural radiance fields (NeRFs) to represent obstacles and the robot itself in 3D. Then, they apply math methods called constrained optimal control to figure out the best path for the robot that avoids crashes. Their simulations show the robot safely navigating through many obstacles using this approach.
safe navigationreachable setsstate spaceneural radiance fields (NeRFs)volumetric representationconstrained optimal controllinear matrix inequalitypath planningroboticsobstacle avoidance
Authors
Omanshu Thapliyal, Malarvizhi Sankaranarayanasamy, Ravigopal Vennelakanti
Abstract
Safe navigation in cluttered environments is an important challenge for autonomous systems. Robots navigating through obstacle ridden scenarios need to be able to navigate safely in the presence of obstacles, goals, and ego objects of varying geometries. In this work, reachable set representations of the robot's real-time capabilities in the state space can be utilized to capture safe navigation requirements. While neural radiance fields (NeRFs) are utilized to compute, store, and manipulate the volumetric representations of the obstacles, or ego vehicle, as needed. Constrained optimal control is employed to represent the resulting path planning problem, involving linear matrix inequality constraints. We present simulation results for path planning in the presence of numerous obstacles in two different scenarios. Safe navigation is demonstrated through using reachable sets in the corresponding constrained optimal control problems.