Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout
Safe L2/L3 driving automation requires anticipating human-in-the-loop reactions during shared-control transitions. While most driving world models forecast the external environment, in-cabin intelligence remains strictly recognition-oriented and lacks multi-step rollout capabilities for driver dynamics. We introduce Driver-WM, a driver-centric latent world model that rolls out in-cabin dynamics causally conditioned on out-cabin traffic context. This formulation unifies physical kinematics forecasting with auxiliary behavioral and emotional semantic recognition. Operating in a compact latent space constructed from frozen vision-language features, Driver-WM adopts a dual-stream architecture to separately encode external traffic and internal driver states. These streams are directionally coupled via a gated causal injection mechanism, which uses a learned vector gate to modulate external contextual perturbations while strictly enforcing temporal causality. Experiments on AIDE show robust long-horizon forecasting on reactive high-motion clips, improved driver/traffic semantic alignment, and controlled interventions that expose the external-to-internal mechanism.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
PeRP: Personalized Residual Policies For Congestion Mitigation Through Co-operative Advisory Systems
Intelligent driving systems can be used to mitigate congestion through simple actions, thus improving many socioeconomic factors such as commute time and gas costs. However, these systems assume precise control over auto…
Pricing is All You Need to Improve Traffic Routing
We investigate the design of pricing policies that enhance driver adherence to route guidance, ensuring effective routing control. The major novelty lies in that we adopt a Markov chain to model drivers' compliance rates…
AllMarkov Regime-Switching Intelligent Driver Model for Interpretable Car-Following Behavior
Accurate and interpretable car-following models are essential for traffic simulation and autonomous vehicle development. However, classical models like the Intelligent Driver Model (IDM) are fundamentally limited by thei…
Bayesian InferenceDiffAttn: Diffusion-Based Drivers' Visual Attention Prediction with LLM-Enhanced Semantic Reasoning
Drivers' visual attention provides critical cues for anticipating latent hazards and directly shapes decision-making and control maneuvers, where its absence can compromise traffic safety. To emulate drivers' perception …
Scene UnderstandingMicroscopic Traffic Simulation by Cooperative Multi-agent Deep Reinforcement Learning
Expert human drivers perform actions relying on traffic laws and their previous experience. While traffic laws are easily embedded into an artificial brain, modeling human complex behaviors which come from past experienc…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)