Related papers: C-TRAIL: A Commonsense World Framework for Traject…

Large-scale task planning is a major challenge. Recent work exploits large language models (LLMs) directly as a policy and shows surprisingly interesting results. This paper shows that LLMs provide a commonsense model of the world in…

Trajectory planning is a core task in autonomous driving, requiring the prediction of safe and comfortable paths across diverse scenarios. Integrating Multi-modal Large Language Models (MLLMs) with Reinforcement Learning (RL) has shown…

Real-world path planning tasks typically involve multiple constraints beyond simple route optimization, such as the number of routes, maximum route length, depot locations, and task-specific requirements. Traditional approaches rely on…

Predicting the near-term behavior of a reactive agent is crucial in many robotic scenarios, yet remains challenging when observations of that agent are sparse or intermittent. Vision-Language Models (VLMs) offer a promising avenue by…

Safety-critical planning in complex environments, particularly at urban intersections, remains a fundamental challenge for autonomous driving. Existing methods, whether rule-based or data-driven, frequently struggle to capture complex scene…

Tool-Integrated Reasoning (TIR) enables large language models (LLMs) to solve complex tasks by interacting with external tools, yet existing approaches depend on high-quality synthesized trajectories selected by scoring functions and sparse…

Achieving fully autonomous driving systems requires learning rational decisions in a wide span of scenarios, including safety-critical and out-of-distribution ones. However, such cases are underrepresented in real-world corpus collected by…

Aligned large language models (LLMs) demonstrate exceptional capabilities in task-solving, following instructions, and ensuring safety. However, the continual learning aspect of these aligned LLMs has been largely overlooked. Existing…

Real-world autonomous driving systems must make safe decisions in the face of rare and diverse traffic scenarios. Current state-of-the-art planners are mostly evaluated on real-world datasets like nuScenes (open-loop) or nuPlan…

Large language models (LLMs) deliver impressive capabilities but incur substantial inference latency and cost, which hinders their deployment in latency-sensitive and resource-constrained scenarios. Cloud-edge-device collaborative inference…

Large language models (LLMs) achieve strong reasoning performance through chain-of-thought (CoT) reasoning, yet often generate unnecessarily long reasoning paths that incur high inference cost. Recent self-consistency-based approaches…

Decision-making and motion planning constitute critical components for ensuring the safety and efficiency of autonomous vehicles (AVs). Existing methodologies typically adopt two paradigms: decision then planning or generation then scoring.…

State-of-the-art (SOTA) urban traffic control increasingly employs Multi-Agent Reinforcement Learning (MARL) to coordinate Traffic Light Controllers (TLCs) and Connected Autonomous Vehicles (CAVs). However, the performance of these systems…

Autonomous driving is a complex task which requires advanced decision making and control algorithms. Understanding the rationale behind the autonomous vehicles' decision is crucial to ensure their safe and effective operation on highway…

Planning safe trajectories under uncertain and dynamic conditions makes the autonomous driving problem significantly complex. Current sampling-based methods such as Rapidly Exploring Random Trees (RRTs) are not ideal for this problem…

Autonomous driving faces critical challenges in rare long-tail events and complex multi-agent interactions, which are scarce in real-world data yet essential for robust safety validation. This paper presents a high-fidelity scenario…

To safely navigate intricate real-world scenarios, autonomous vehicles must be able to adapt to diverse road conditions and anticipate future events. World model (WM) based reinforcement learning (RL) has emerged as a promising approach by…

We explore the geospatial reasoning capabilities of Large Language Models (LLMs), specifically, whether LLMs can read road network maps and perform navigation. We frame trajectory recovery as a proxy task, which requires models to…

Traditional autonomous driving methods adopt a modular design, decomposing tasks into sub-tasks. In contrast, end-to-end autonomous driving directly outputs actions from raw sensor data, avoiding error accumulation. However, training an…

Autonomous driving technology, a catalyst for revolutionizing transportation and urban mobility, has the tend to transition from rule-based systems to data-driven strategies. Traditional module-based systems are constrained by cumulative…