This work proposes RFWorld, a Rollout-Free World model for end-to-end trajectory evaluation, which constructs a shared scene memory and shapes it into a future-readable representation via lightweight training-time temporal readout with semantic supervision, keeping training overhead low.
Abstract
Although existing candidate trajectory evaluators have substantially improved end-to-end planning accuracy, their underlying mechanism remains suboptimal. Model-based evaluators typically make scoring future-aware by explicitly predicting candidate-conditioned future states over the planning horizon, which we term rollout. However, rollout incurs high inference cost and accumulates prediction errors. We argue that planning does not require reconstructing a full future scene for each candidate, but only future-relevant information for reliable comparison. We therefore propose RFWorld, a Rollout-Free World model for end-to-end trajectory evaluation. RFWorld constructs a shared scene memory and shapes it into a future-readable representation via lightweight training-time temporal readout with semantic supervision, keeping training overhead low. At inference time, candidate trajectories directly query the shared memory via sparse spatial readout for scoring, reducing computation by roughly the planning horizon times the number of candidate trajectories, while avoiding recursive rollout errors. Experiments on NAVSIM and Bench2Drive show that RFWorld learns a more planning-aligned world representation and achieves state-of-the-art performance.
This work proposes FPD-Drive, an end-to-end planner that distills privileged future knowledge into a visual driving policy to improve both multi-trajectory supervision and safety selection, and introduces Future-Privileged Multi-Target Distillation to transfer diverse, high-quality trajectory targets from a teacher wit...
Li-Heng Chen, Qifeng Chen, Cheng-Wei Wu et al.· 1 citation
Candidate-based end-to-end driving planners reason over a finite set of trajectory hypotheses. However, for sparse planners, a limited candidate set may provide insufficient support for scene-relevant maneuvers, while fixed downstream candidate budgets do not account for prediction uncertainty. To address these challen...
Fabian Schmidt, Karol Fedurko, Markus Enzweiler et al.· 0 citations
This work proposes FeasibleFlow, a one-step end-to-end generative framework that jointly transports a configuration-space feasibility field and multimodal ego trajectories and introduces the Anchor-relative ranker (ARR) and Pareto-ReinFlow to balance safety and progress in candidate selection and generation.
Autonomous driving requires choosing a safe and efficient plan as surrounding traffic evolves. Generate-and-select planners propose multiple trajectories and score them for execution, and they have outperformed representative direct-prediction baselines on NAVSIM. Their scorer must compare plans that were never execute...
Jie-Yuan Pei, Mei-Yi Lu, Sining Ang et al.· arXiv.org· 0 citations
Evaluating robot policies before deployment typically requires producing new trajectories through real-world execution, simulators, or learned world models. These rollout-based approaches impose infrastructure requirements; simulator and world-model evaluators additionally face prediction errors that can compound over...
Yun-Fu Deng, Sang-Woo Shin, Brahma S. Pavse et al.· 0 citations
Multimodal trajectory prediction improves behavioral coverage in end-to-end autonomous driving, but existing methods remain limited by sparse scene representations. Incomplete evidence leads to low-quality candidate generation and unreliable ranking among geometrically similar trajectories. On a register-based baseline...
Jia-Xing Chen, Heng-Duo Zou, Yu-Kai Qin et al.· 0 citations
From feet to fingertips — we are teaching robots intelligent whole-body control, fine dexterity, and teamwork to complete a broad range of complex tasks.