AI & ML
TrajWAM: Trajectory-Conditioned Future Learning for Vision-Language Driving
arXiv cs.RO0 views
arXiv:2611.24192v1 Announce Type: cross Abstract: World Action Models (WAMs) connect future scene prediction with action planning for autonomous driving. Each driving record pairs an executed ego trajectory with its observed future, providing a factual outcome for learning this connection. We present TrajWAM, a trajectory-conditioned WAM that improves vision-language driving through auxiliary bird's-eye-view (BEV) future learning. An ego-trajectory query conditions DINOv3-aligned BEV predictions from shared planner representations. Training combines factual reconstruction under the executed trajectory with one-sided feature separation under an unlabeled perturbed trajectory. Together, these objectives train the shared planner to generate driving waypoints. Native inference directly generates waypoints and bypasses the auxiliary future-prediction branch. On all 220 Bench2Drive routes, TrajWAM achieves 91.53 Driving Score and 75.45% Success Rate, exceeding a schedule-matched planning-only fine-tuning baseline by 5.31 Driving Score points and eight successful routes.
Source:https://arxiv.org/abs/2611.24192PreviousAdaptive Action Horizon Selection via Flow-Field UncertaintyNextElephantAgent: Contextual State Continuity in Agentic Systems
Related posts
Adaptive Action Horizon Selection via Flow-Field Uncertainty
0arXiv cs.RO
Object Pose: The Link between Weak Perspective, Paraperspective, and Full Perspective
0arXiv cs.RO
Attention Is Not Relevance: Challenging the Causality of Attention in Autonomous Driving
0arXiv cs.RO
DOCK: Dual-Stream-Inspired Self-Supervised Object-Centric Representations Grounded in Robot Kinematics
0arXiv cs.RO
Hebbian self-organization of monosynaptic reflexes in a biologically realistic multiarticular limb
0arXiv cs.RO
Neural Circuit Architectural Priors for Rat Locomotion
0arXiv cs.RO