MeshSIPP: Efficient Lattice Planning in Dynamic Environment

2026-10-07

AI Summary

This study addresses the computational bottleneck in motion planning arising from the coupling of high-branching motion primitives with time-varying obstacles in dynamic environments. To overcome this, we propose an acceleration framework based on spatial beam propagation. By exploiting the spatial overlap among primitives, they are modeled as spatial beams for forward propagation, enabling time-aware pruning through lightweight bounding-box checks. Furthermore, a deferred exact search strategy is introduced to eliminate redundant computations. This approach significantly reduces solving overhead while strictly guaranteeing completeness and optimality. Evaluated on over 6,000 benchmark instances, the proposed method achieves up to a threefold speedup compared to state-of-the-art spatiotemporal planners. Its practical effectiveness is further validated through real-time simulations in ROS 2.

Abstract

Autonomous navigation in dynamic environments requires computing spatiotemporal trajectories that satisfy non-holonomic motion constraints. When the trajectories of the moving obstacles are predictable or known, a promising approach is to rely on the combination of state lattices constructed from precomputed feasible motion primitives and Safe Interval Path Planning -- a search-based algorithm with strong theoretical guarantees. While this approach yields feasible paths, the rich primitive sets needed for smooth navigation induce a large branching factor, which becomes costly when coupled with time-dependent obstacle intervals. To this end, we present MeshSIPP, an efficient planner that removes the computational bottleneck by exploiting the fact that many primitives sweep the same regions and can therefore be validated together. MeshSIPP propagates primitives as spatial bundles, screens them with lightweight bounding-interval checks, and defers the expensive exact departure-time search until a primitive reaches its terminal state. A time-aware pruning rule additionally discards redundant space-time branches early in the search. We prove that the resulting search is complete and optimal. Extensive experiments over more than 6,000 benchmark instances and real-time ROS~2 simulations show that MeshSIPP achieves up to a 3$\times$ speedup over state-of-the-art spatiotemporal planners.

Problem

• dynamic environment
• autonomous navigation
• state lattice
• Safe Interval Path Planning
• computational bottleneck

Innovation

• Safe Interval Path Planning
• State Lattice
• Motion Primitives
• Dynamic Environment
• Spatiotemporal Planning