{"ID":2855880,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.12733","arxiv_id":"2510.12733","title":"HYPE: Hybrid Planning with Ego Proposal-Conditioned Predictions","abstract":"Safe and interpretable motion planning in complex urban environments needs to reason about bidirectional multi-agent interactions. This reasoning requires to estimate the costs of potential ego driving maneuvers. Many existing planners generate initial trajectories with sampling-based methods and refine them by optimizing on learned predictions of future environment states, which requires a cost function that encodes the desired vehicle behavior. Designing such a cost function can be very challenging, especially if a wide range of complex urban scenarios has to be considered. We propose HYPE: HYbrid Planning with Ego proposal-conditioned predictions, a planner that integrates multimodal trajectory proposals from a learned proposal model as heuristic priors into a Monte Carlo Tree Search (MCTS) refinement. To model bidirectional interactions, we introduce an ego-conditioned occupancy prediction model, enabling consistent, scene-aware reasoning. Our design significantly simplifies cost function design in refinement by considering proposal-driven guidance, requiring only minimalistic grid-based cost terms. Evaluations on large-scale real-world benchmarks nuPlan and DeepUrban show that HYPE effectively achieves state-of-the-art performance, especially in safety and adaptability.","short_abstract":"Safe and interpretable motion planning in complex urban environments needs to reason about bidirectional multi-agent interactions. This reasoning requires to estimate the costs of potential ego driving maneuvers. Many existing planners generate initial trajectories with sampling-based methods and refine them by optimiz...","url_abs":"https://arxiv.org/abs/2510.12733","url_pdf":"https://arxiv.org/pdf/2510.12733v2","authors":"[\"Hang Yu\",\"Julian Jordan\",\"Julian Schmidt\",\"Silvan Lindner\",\"Alessandro Canevaro\",\"Wilhelm Stork\"]","published":"2025-10-14T17:11:04Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\",\"cs.LG\"]","methods":"[]","has_code":false}