13 accepted papers
Trajectory prediction for traffic agents is critical for safe autonomous driving. However, achieving effective zero-shot generalization in previously unseen domains remains a significant challenge. Motivated by the consistent nature of kinematics across diverse domains, we aim to incorporate domain-…
Proactive large language model (LLM) agents aim to actively plan, query, and interact over multiple turns, enabling efficient task completion beyond passive instruction following and making them essential for real-world, user-centric applications. Agentic reinforcement learning (RL) has recently eme…
Trajectory world models play a crucial role in robotic dynamics learning, planning, and control. While recent works have explored trajectory world models for diverse robotic systems, they struggle to scale to a large number of distinct system dynamics and overlook domain knowledge of physical struct…
This work aims to address the problem of long-term dynamic forecasting in complex environments where data are noisy and irregularly sampled. While recent studies have introduced some methods to improve prediction performance, these approaches still face a significant challenge in handling long-term…
Simulation is critical for safety evaluation in autonomous driving, particularly in capturing complex interactive behaviors. However, generating **realistic** and **controllable** traffic scenarios in long-tail situations remains a significant challenge. Existing generative models suffer from the co…
End-to-end (E2E) autonomous driving models have demonstrated strong performance in open-loop evaluations but often suffer from cascading errors and poor generalization in closed-loop settings. To address this gap, we propose Model-based Policy Adaptation (MPA), a general framework that enhances the…
Offline model-based reinforcement learning (MBRL) enhances data efficiency by utilizing pre-collected datasets to learn models and policies, especially in scenarios where exploration is costly or infeasible. Nevertheless, its performance often suffers from the objective mismatch between model and po…
Furniture assembly remains an unsolved problem in robotic manipulation due to its long task horizon and nongeneralizable operations plan. This paper presents the Tactile Ensemble Skill Transfer (TEST) framework, a pioneering offline reinforcement learning (RL) approach that incorporates tactile feed…
Offline safe reinforcement learning (RL) aims to train a policy that satisfies con- straints using a pre-collected dataset. Most current methods struggle with the mismatch between imperfect demonstrations and the desired safe and rewarding performance. In this paper, we mitigate this issue from a da…
In the domain of autonomous driving, the offline Reinforcement Learning (RL) approaches exhibit notable efficacy in addressing sequential decision-making problems from offline datasets. However, maintaining safety in diverse safety-critical scenarios remains a significant challenge due to long-taile
Generating safety-critical scenarios, which are crucial yet difficult to collect, provides an effective way to evaluate the robustness of autonomous driving systems. However, the diversity of scenarios and efficiency of generation methods are heavily restricted by the rareness and structure of safet…
As a pivotal component to attaining generalizable solutions in human intelligence, reasoning provides great potential for reinforcement learning (RL) agents' generalization towards varied goals by summarizing part-to-whole arguments and discovering cause-and-effect relations. However, how to discove…
The Controllable Variational Autoencoder (ControlVAE) combines automatic control theory with the basic VAE model to manipulate the KL-divergence for overcoming posterior collapse and learning disentangled representations. It has shown success in a variety of applications, such as image generation, d…