AI & ML
Improving While Deployed: Learning Proactive End-to-End Driving from Imperfect Human Takeover Data
arXiv cs.RO0 views
arXiv:2611.23719v1 Announce Type: new Abstract: Once deployed on vehicles, end-to-end driving models continuously encounter challenging scenarios, generating valuable human takeover data that capture both model outputs and human behaviors. However, human interventions are often imperfect, as drivers may intervene too late or unnecessarily. Consequently, direct imitation can reinforce late responses or discourage otherwise appropriate maneuvers. To address this challenge, we propose an offline post-training framework that transforms imperfect takeover data into proactive supervision. We first construct diverse trajectory candidates by augmenting the plans of the deployed model and shifting recorded human corrective maneuvers earlier in time. We then train a scene-conditioned trajectory scorer to rank these candidates using expert demonstrations and unpaired preference signals from takeover logs. Using this scorer, we selectively replace pre-takeover training targets with higher-scoring candidates while retaining the original targets in normal driving scenarios. Finally, we distill the resulting targets into the driving model without changing its inference architecture. In closed-loop evaluations using real-world scenarios reconstructed with 4D Gaussian splatting, our method achieves the highest overall success rate, outperforming the deployed model, direct imitation learning and trajectory post-optimization. These results highlight a practical path toward efficient updates of deployed driving models using existing fleet logs.
Source:https://arxiv.org/abs/2611.23719PreviousExecGap: Exploiting Command-Execution Gap for Patch Attacks on Vision-Language-Action ModelsNextRecallFlow: Episodic Memory as the Source Distribution of Generative Robot Policies
Related posts
Streaming Generative Video Compression with Embedding Alignment and In-Context Propagation
0arXiv eess.IV
Beyond Accuracy: Benchmarking Uncertainty Quantification in Retinal Disease Screening
0arXiv eess.IV
CiGS: Conduction in Gaussian Splats for Interior Temperature Field from Thermal Images
0arXiv cs.GR
Probing Physics in Motion Diffusion Models Against Their Own Estimate
0arXiv cs.GR
NIRJALA: Draining the Sea out of Gaussian Splatting with Three-Path Optics and Reversible Physics
0arXiv cs.GR
How Music LLMs Actually Work: From Tokens to Waves (MusicGen, DiT, and Building Your Own Engine)
0dev.to Machine Learning