{"ID":2858893,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.07210","arxiv_id":"2510.07210","title":"HyPlan: Hybrid Learning-Assisted Planning Under Uncertainty for Safe Autonomous Driving","abstract":"We present a novel hybrid learning-assisted planning method, named HyPlan, for solving the collision-free navigation problem for self-driving cars in partially observable traffic environments. HyPlan combines methods for multi-agent behavior prediction, deep reinforcement learning with proximal policy optimization and approximated online POMDP planning with heuristic confidence-based vertical pruning to reduce its execution time without compromising safety of driving. Our experimental performance analysis on the CARLA-CTS2 benchmark of critical traffic scenarios with pedestrians revealed that HyPlan may navigate safer than selected relevant baselines and perform significantly faster than considered alternative online POMDP planners.","short_abstract":"We present a novel hybrid learning-assisted planning method, named HyPlan, for solving the collision-free navigation problem for self-driving cars in partially observable traffic environments. HyPlan combines methods for multi-agent behavior prediction, deep reinforcement learning with proximal policy optimization and...","url_abs":"https://arxiv.org/abs/2510.07210","url_pdf":"https://arxiv.org/pdf/2510.07210v2","authors":"[\"Donald Pfaffmann\",\"Matthias Klusch\",\"Marcel Steinmetz\"]","published":"2025-10-08T16:44:54Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}