Safe Navigation using Neural Radiance Fields via Reachable Sets
For autonomous systems requiring safe navigation in cluttered environments, the approach integrates NeRFs with reachable sets, but results are limited to simulations without real-world validation or quantitative comparisons.
The paper tackles safe navigation in cluttered environments by combining reachable sets with neural radiance fields (NeRFs) and constrained optimal control. Simulation results demonstrate safe path planning in two obstacle scenarios.
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.