Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Hybrid-Prediction Integrated Planning for Autonomous Driving
Haochen Liu, Zhiyu Huang, Wenhui Huang, Haohan Yang, Xiaoyu Mo, Chen Lv
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add collision-reasoning loss L_col (ablation) | HPP planner · nuScenes hybrid guidance ablation | collision rate avg (%): 0.39 -> 0.31 | Improved |
| add occupancy and full-motion guidance to L_col (ablation) | HPP planner · nuScenes hybrid guidance ablation | collision rate avg (%): 0.31 -> 0.15 | Improved |
| add occupancy guidance (joint prediction) to planning (ablation) | HPP · nuScenes hybrid guidance ablation | planning error avg (m): 0.60 -> 0.72 | Hurt |
| add agent-conditioned occupancy and motion fusion in MS-OccFormer (ablation) | HPP · nuScenes co-design ablation | IoU-near: 61.9 -> 63.7 | Improved |
| add score scaling in MS-OccFormer (ablation) | HPP · nuScenes co-design ablation | collision rate (%): 0.428 -> 0.402 | Mixed |
| add the GTFormer reasoning module (ablation) | HPP · nuScenes co-design ablation | miss rate: +3.1% MR | Improved |
| add joint dependencies in GTFormer (ablation) | HPP · nuScenes co-design ablation | minADE: +1.7% minADE | Improved |
| add hybrid prediction interactions in Ego Planner (ablation) | HPP · nuScenes co-design ablation | collision rate: -0.047% CR | Improved |
| add global integration in occupancy prediction (ablation) | HPP · nuScenes occupancy ablation | IoU-near: 61.6 -> 63.7 | Improved |
| add local integration in occupancy prediction (ablation) | HPP · nuScenes occupancy ablation | VPQ-near: 52.8 -> 55.0 | Improved |
| add attention mask Mt (ablation) | HPP · nuScenes occupancy ablation | VPQ-near: 53.8 -> 55.0 | Improved |
| add ego status to HPP planner | HPP · nuScenes open-loop planning | planning error avg (m): 0.97 -> 0.72 | Improved |
Closest papers by meaning
- Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving (AAAI 2025 · similarity 0.88)
- Int2Planner: An Intention-based Multi-modal Motion Planner for Integrated Prediction and Planning (AAAI 2025 · similarity 0.88)
- AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving (NeurIPS 2026 · similarity 0.87)
- Diffusion-Based Planning for Autonomous Driving with Flexible Guidance (ICLR 2025 · similarity 0.87)
- $AutoDrive\text{-}P^3$: Unified Chain of Perception–Prediction–Planning Thought via Reinforcement Fine-Tuning (ICLR 2026 · similarity 0.87)
- Graph-Based Prediction and Planning Policy Network (GP3Net) for Scalable Self-Driving in Dynamic Environments Using Deep Reinforcement Learning (AAAI 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
