Goal-Oriented Reactive Simulation for Closed-Loop Trajectory Prediction
cs.RO
Submitted: 2026-03-25
Updated: 2026-09-18
Comments: The core claim that the simulation becomes reactive does not hold, even though the findings on its effects on the ego vehicle remain valid. This claim was re-evaluated based on reviewer feedback, and the paper is therefore being retracted. However, the valid results regarding the effects on the ego vehicle are being merged into the parallel study: https://arxiv.org/abs/2603.23393
Code: https://github.com/harshy105/CL-Traj
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst
- Closing the Loop: Motion Prediction Models beyond Open-Loop Benchmarks
- MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction
- GoRela: Go Relative for Viewpoint-Invariant Motion Forecasting
- Robust Autonomy Emerges from Self-Play
- Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction
- CaRL: Learning Scalable Planning Policies with Simple Rewards
- DONUT: A Decoder-Only Model for Trajectory Prediction
- SEPT: Towards Efficient Scene Representation Learning for Motion Prediction
- UniMM: A Unified Mixture Model Framework for Multi-Agent Simulation
- Scene Transformer: A unified architecture for predicting multiple agent trajectories
- Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting
- Rectify, Don't Regret: On-Policy Closed-Loop Training for Multimodal Trajectory Prediction
- Contingency Planning for Safety-Critical Autonomous Vehicles: A Review and Perspectives
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies