The Real2Sim2Real (R2S2R) paradigm is critical for advancing robotic learning. Existing methods lack a comprehensive solution to accurately reconstruct real-world objects with both spatial representations and their associated physics attributes in the Real2Sim stage. We propose a Real2Sim pipeline to generate digital assets enabling high-fidelity simulation. We design a hybrid repre-sentation model that integrates mesh geometry, 3D Gaussian kernels, and physics attributes to enhance the representation of robotic arms in digital assets. This hybrid representation is implemented through a Gaussian-Mesh-Pixel binding technique, which establishes an isomorphic mapping between mesh vertices and the Gaussian model. This enables a fully differentiable rendering pipeline that can be optimized through numerical solvers, achieves high-fidelity rendering via Gaussian Splatting, and facilitates physically plausible simulation of the robotic arm's interaction with its environment through mesh geometry. With the digital assets, we propose a fully manipulable Real2Sim pipeline that standardizes coordinate systems and scales, ensuring the seamless integration of multiple components. To demonstrate its effectiveness, we include datasets covering various robotic manipulation tasks with their mesh reconstructions. Our model achieves state-of-the-art results in realistic rendering and mesh reconstruction quality for robotic applications. Our code and datasets will be made publicly available at robostudioapp.com.

Robot manipulation relies on accurately predicting contact points and end-effector directions to ensure successful operation. However, learning-based robot manipulation, trained on a limited category within a simulator, often struggles to achieve generalizability, especially when confronted with extensive categories. Therefore, we introduce an innovative approach for robot manipulation that leverages the robust reasoning capabilities of Multimodal Large Language Models (MLLMs) to enhance the stability and generalization of manipulation. By fine-tuning the injected adapters, we preserve the inherent common sense and reasoning ability of the MLLMs while equipping them with the ability for manipulation. The fundamental insight lies in the introduced fine-tuning paradigm, encompassing object category understanding, affordance prior reasoning, and object-centric pose prediction to stimulate the reasoning ability of MLLM in manipulation. During inference, our approach utilizes an RGB image and text prompt to predict the end effector's pose in chain of thoughts. After the initial contact is established, an active impedance adaptation policy is introduced to plan the upcoming way-points in a closed-loop manner. Moreover, in real world, we design a test-time adaptation (TTA) strategy for manipulation to enable the model better adapt to the current real-world scene configuration. Experiments in simulator and real-world show the promising performance of Mani-pLLM. More details and demonstrations can be found at https://sites.google.com/view/manipllm.

Robotic manipulation requires accurate perception of the environment, which poses a significant challenge due to its inherent complexity and constantly changing nature. In this context, RGB image and point-cloud observations are two commonly used modalities in visual-based robotic manipulation, but each of these modalities have their own limitations. Commercial point-cloud observations often suffer from issues like sparse sampling and noisy output due to the limits of the emission-reception imaging principle. On the other hand, RGB images, while rich in texture information, lack essential depth and 3D information crucial for robotic manipulation. To mitigate these challenges, we propose an image-only robotic manipulation framework that leverages an eye-on-hand monocular camera installed on the robot’s parallel gripper. By moving with the robot gripper, this camera gains the ability to actively perceive the object from multiple perspectives during the manipulation process. This enables the estimation of 6D object poses, which can be utilized for manipulation. While, obtaining images from more and diverse viewpoints typically improves pose estimation, it also increases the manipulation time. To address this trade-off, we employ a reinforcement learning policy to synchronize the manipulation strategy with active perception, achieving a balance between 6D pose accuracy and manipulation efficiency. Our experimental results in both simulated and real-world environments showcase the state-of-the-art effectiveness of our approach. We believe that our method will inspire further research on real-world-oriented robotic manipulation. See https://rgbmanip.github.io/ for more details.

AI systems empowered by reinforcement learning (RL) algorithms harbor the immense potential to catalyze societal advancement, yet their deployment is often impeded by significant safety concerns. Particularly in safety-critical applications, researchers have raised concerns about unintended harms or unsafe behaviors of unaligned RL agents. The philosophy of safe reinforcement learning (SafeRL) is to align RL agents with harmless intentions and safe behavioral patterns. In SafeRL, agents learn to develop optimal policies by receiving feedback from the environment, while also fulfilling the requirement of minimizing the risk of unintended harm or unsafe behavior. However, due to the intricate nature of SafeRL algorithm implementation, combining methodologies across various domains presents a formidable challenge. This had led to an absence of a cohesive and efficacious learning framework within the contemporary SafeRL research milieu. In this work, we introduce a foundational framework designed to expedite SafeRL research endeavors. Our comprehensive framework encompasses an array of algorithms spanning different RL domains and places heavy emphasis on safety elements. Our efforts are to make the SafeRL-related research process more streamlined and efficient, therefore facilitating further research in AI safety.

Achieving human-level dexterity in robotics remains a critical open problem. Even simple dexterous manipulation tasks pose significant difficulties due to the high number of degrees of freedom and the need for cooperation among heterogeneous agents (e.g., finger joints). While some researchers have utilized reinforcement learning (RL) to control a single hand in manipulating objects, tasks that require coordinated bimanual cooperation are still under-explored due to the fewer suitable environments, which can result in difficulties and sub-optimal performance. To address these challenges, we introduce Bi-DexHands, a simulator with two dexterous hands featuring 20 bimanual manipulation tasks and thousands of target objects, designed to match various levels of human motor skills based on cognitive science research. We developed Bi-DexHands in Issac Gym, enabling highly efficient RL training at over 30,000 frames per second using a single NVIDIA RTX 3090. Based on Bi-DexHands, we present a comprehensive evaluation of popular RL algorithms in different settings, including single-agent/multi-agent RL, offline RL, multi-task RL, and meta RL. Our findings show that on-policy algorithms, such as PPO, can master simple manipulation tasks that correspond to those of 48-month-old babies, such as catching a flying object or opening a bottle. Furthermore, multi-agent RL can improve the ability to perform manipulations that require skilled bimanual cooperation, such as lifting a pot or stacking blocks. Despite achieving success in individual tasks, current RL algorithms struggle to learn multiple manipulation skills in most multi-task and few-shot learning scenarios. This highlights the need for further research and development within the RL community.

Learning a generalizable object manipulation policy is vital for an embodied agent to work in complex real-world scenes. Parts, as the shared components in different object categories, have the potential to increase the generalization ability of the manipulation policy and achieve cross-category object manipulation. In this work, we build the first large-scale, part-based cross-category object manipulation benchmark, PartManip, which is composed of 11 object categories, 494 objects, and 1432 tasks in 6 task classes. Compared to previous work, our benchmark is also more diverse and realistic, i.e., having more objects and using sparse-view point cloud as input without oracle information like part segmentation. To tackle the difficulties of vision-based policy learning, we first train a statebased expert with our proposed part-based canonicalization and part-aware rewards, and then distill the knowledge to a vision-based student. We also find an expressive backbone is essential to overcome the large diversity of different objects. For cross-category generalization, we introduce domain adversarial learning for domain-invariant feature extraction. Extensive experiments in simulation show that our learned policy can outperform other methods by a large margin, especially on unseen object categories. We also demonstrate our method can successfully manipulate novel objects in the real world. Our benchmark has been released in https://pku-epic.github.io/PartManip.

In this work, we tackle 6-DoF grasp detection for transparent and specular objects, which is an important yet challenging problem in vision-based robotic systems, due to the failure of depth cameras in sensing their geometry. We, for the first time, propose a multiview RGB-based 6-DoF grasp detection network, GraspNeRF, that leverages the generalizable neural radiance field (NeRF) to achieve material-agnostic object grasping in clutter. Compared to the existing NeRF-based 3-DoF grasp detection methods that rely on densely captured input images and time-consuming per-scene optimization, our system can perform zero-shot NeRF construction with sparse RGB inputs and reliably detect 6-DoF grasps, both in real-time. The proposed framework jointly learns generalizable NeRF and grasp detection in an end-to-end manner, optimizing the scene representation construction for the grasping. For training data, we generate a large-scale photorealistic domain-randomized synthetic dataset of grasping in cluttered tabletop scenes that enables direct transfer to the real world. Our extensive experiments in synthetic and real-world environments demonstrate that our method significantly outperforms all the baselines in all the experiments while remaining in real-time. Project page can be found at https://pku-epic.github.io/GraspNeRF.

Learning to manipulate 3D objects in an interactive environment has been a challenging problem in Reinforcement Learning (RL). In particular, it is hard to train a policy that can generalize over objects with different semantic categories, diverse shape geometry and versatile functionality. In this study, we focused on the contact information in manipulation processes, and proposed a unified representation for critical interactions to describe different kinds of manipulation tasks. Specifically, we take advantage of the contact information generated during the RL training process and employ it as unified visual representation to predict contact map of interest. Such representation leads to an end-to-end learning framework that combined affordance based and RL based methods for the first time. Our unified framework can generalize over different types of manipulation tasks. Surprisingly, the effectiveness of such framework holds even under the multi-stage and multi-agent scenarios. We tested our method on eight types of manipulation tasks. Results showed that our methods outperform baseline algorithms, including visual affordance methods and RL methods, by a large margin on the success rate. The demonstration can be found at https://sites.google.com/view/rlafford/.

Generating dexterous grasping has been a long-standing and challenging robotic task. Despite recent progress, existing methods primarily suffer from two issues. First, most prior art focuses on a specific type of robot hand, lacking generalizable capability of handling unseen ones. Second, prior arts oftentimes fail to rapidly generate diverse grasps with a high success rate. To jointly tackle these challenges with a unified solution, we propose the GenDexGrasp, a novel hand-agnostic grasping algorithm for generalizable grasping. GenDexGrasp is trained on our proposed large-scale multi-hand grasping dataset MultiDex synthesized with force closure optimization. By leveraging the contact map as a hand-agnostic intermediate representation, GenDexGrasp efficiently generates diverse and plausible grasping poses with a high success rate and can transfer among diverse multi-fingered robotic hands. Compared with previous methods, GenDexGrasp achieves a three-way trade-off among success rate, inference speed, and diversity.

Artificial intelligence (AI) systems possess significant potential to drive societal progress. However, their deployment often faces obstacles due to substantial safety concerns. Safe reinforcement learning (SafeRL) emerges as a solution to optimize policies while simultaneously adhering to multiple constraints, thereby addressing the challenge of integrating reinforcement learning in safety-critical scenarios. In this paper, we present an environment suite called Safety-Gymnasium, which encompasses safety-critical tasks in both single and multi-agent scenarios, accepting vector and vision-only input. Additionally, we offer a library of algorithms named Safe Policy Optimization (SafePO), comprising 16 state-of-the-art SafeRL algorithms. This comprehensive library can serve as a validation tool for the research community. By introducing this benchmark, we aim to facilitate the evaluation and comparison of safety performance, thus fostering the development of reinforcement learning for safer, more reliable, and responsible real-world applications. The website of this project can be accessed at https://sites.google.com/view/safety-gymnasium.