相关论文: Evaluating Gemini Robotics Policies in a Veo World…

Humanoid robots, with their human-like form, are uniquely suited for interacting in environments built for people. However, enabling humanoids to reason, plan, and act in complex open-world settings remains a challenge. World models, models…

The model-based estimation of 3D animal pose and shape from images enables computational modeling of animal behavior. Training models for this purpose requires large amounts of labeled image data with precise pose and shape annotations.…

Simulation-based testing has emerged as an essential tool for verifying and validating autonomous vehicles (AVs). However, contemporary methodologies, such as deterministic and imitation learning-based driver models, struggle to capture the…

The rapid proliferation of multimodal generative models has sparked critical discussions on their reliability, fairness and potential for misuse. While text-to-image models excel at producing high-fidelity, user-guided content, they often…

We focus on developing efficient and reliable policy optimization strategies for robot learning with real-world data. In recent years, policy gradient methods have emerged as a promising paradigm for training control policies in simulation.…

This survey provides a comprehensive review on recent advancements of generative learning models in robotic manipulation, addressing key challenges in the field. Robotic manipulation faces critical bottlenecks, including significant…

Learning-based methods have improved locomotion skills of quadruped robots through deep reinforcement learning. However, the sim-to-real gap and low sample efficiency still limit the skill transfer. To address this issue, we propose an…

The vision and language generative models have been overgrown in recent years. For video generation, various open-sourced models and public-available services have been developed to generate high-quality videos. However, these methods often…

Generative AI (GenAI) models have revolutionized animation, enabling the synthesis of humans and motion patterns with remarkable visual fidelity. However, generating truly realistic human animation remains a formidable challenge, where even…

Learning robust and generalizable world models is crucial for enabling efficient and scalable robotic control in real-world environments. In this work, we introduce a novel framework for learning world models that accurately capture…

Comprehensive, unbiased, and comparable evaluation of modern generalist policies is uniquely challenging: existing approaches for robot benchmarking typically rely on heavy standardization, either by specifying fixed evaluation tasks and…

Zero-shot generalization across various robots, tasks and environments remains a significant challenge in robotic manipulation. Policy code generation methods use executable code to connect high-level task descriptions and low-level action…

Reinforcement Learning (RL) has shown great potential in refining robotic manipulation policies, yet its efficacy remains strongly bottlenecked by the difficulty of designing generalizable reward functions. In this paper, we propose a…

The next generation of autonomous agents must not only learn efficiently but also act reliably and adapt their behavior in open worlds. Standard approaches typically assume fixed tasks and environments with little or no novelty, which…

End-to-end visuomotor policies trained using behavior cloning have shown a remarkable ability to generate complex, multi-modal low-level robot behaviors. However, at deployment time, these policies still struggle to act reliably when faced…

For autonomous vehicles, safe navigation in complex environments depends on handling a broad range of diverse and rare driving scenarios. Simulation- and scenario-based testing have emerged as key approaches to development and validation of…

The ability to simulate the effects of future actions on the world is a crucial ability of intelligent embodied agents, enabling agents to anticipate the effects of their actions and make plans accordingly. While a large body of existing…

The strong performance of large vision-language models (VLMs) trained with reinforcement learning (RL) has motivated similar approaches for fine-tuning vision-language-action (VLA) models in robotics. Many recent works fine-tune VLAs…

Learning from few demonstrations to develop policies robust to variations in robot initial positions and object poses is a problem of significant practical interest in robotics. Compared to imitation learning, which often struggles to…

Visual navigation models based on deep learning can learn effective policies when trained on large amounts of visual observations through reinforcement learning. Unfortunately, collecting the required experience in the real world requires…