Event
Uncertainty-aware collision avoidance pipeline achieves zero collisions
1 reports · 1 sources
Doris Xu and other authors submitted a paper proposing a modular perception-prediction-planning pipeline that passes uncertainty between modules as a structured, interpretable quantity and guarantees a feasible solution in every cycle within a convex safe set. The authors claim that in Monte Carlo trials at a four-way unsignalized intersection, the pipeline achieved 0% collisions and 0% solver infeasibility, with a per-cycle runtime of 12.7 ms; the collision rates of the deterministic planner and the chance-constrained baseline were 36% and 10%, respectively. Ablation experiments confirmed the necessity of each uncertainty source, and a hardware deployment on a Clearpath Jackal UGV verified real-time feasibility. All the above results are as reported by the authors.
Report timeline
- Interpretable Collision Avoidance and Feasibility Guarantees via an Uncertainty-Aware Pipeline
The study proposes a modular perception-prediction-planning pipeline that propagates uncertainty as structured, interpretable quantities across modules and guarantees a feasible solution in every cycle within convex safe sets. In Monte Carlo trials at a four-way unsignalized intersection, the pipeline achieved 0% collisions and 0% solver infeasibility, with 12.7 ms per cycle; the deterministic planner and chance-constrained baseline had collision rates of 36% and 10%, respectively. Ablation experiments confirmed the necessity of each uncertainty source, and a hardware deployment on a Clearpath Jackal UGV verified real-time feasibility.
arXiv cs.RO ·