Recent advances in dexterous grasping synthesis have demonstrated significant progress in producing reasonable and plausible grasps for many task purposes. But it remains challenging to generalize to unseen object categories and diverse task instructions. In this paper, we propose G-DexGrasp, a retrieval-augmented generation approach that can produce high-quality dexterous hand configurations for unseen object categories and language-based task instructions. The key is to retrieve generalizable grasping priors, including the fine-grained contact part and the affordance-related distribution of relevant grasping instances, for the following synthesis pipeline. Specifically, the fine-grained contact part and affordance act as generalizable guidance to infer reasonable grasping configurations for unseen objects with a generative model, while the relevant grasping distribution plays as regularization to guarantee the plausibility of synthesized grasps during the subsequent refinement optimization. Our comparison experiments validate the effectiveness of our key designs for generalization and demonstrate the remarkable performance against the existing approaches.

UP provides a simple and general two-stage training method for humanoid getting-up tasks, which can be directly deployed on Unitree G1 humanoid robots [70]. Our policies showcase robust and smooth behavior that can get up from diverse lying postures (both supine and prone) on varied terrains such as grass slopes and stone tile. Abstract--Automatic fall recovery is a crucial prerequisite robust to variations in initial configuration and terrains. We find before humanoid robots can be reliably deployed. Hand-designing these innovations enable a real-world G1 humanoid robot to get controllers for getting up is difficult because of the varied up from two main situations that we considered: a) lying face up configurations a humanoid can end up in after a fall and the and b) lying face down, both tested on flat, deformable, slippery challenging terrains humanoid robots are expected to operate surfaces and slopes (e.g., sloppy grass and snowfield). This paper develops a learning framework to produce of our knowledge, this is the first successful demonstration of controllers that enable humanoid robots to get up from varying learned getting-up policies for human-sized humanoid robots in configurations on varying terrains. Stage II is optimized to track the robots), a humanoid robot may end up in an unpredictable state trajectory discovered in the first stage to tackle easier configuration upon a fall, or may be on an unknown terrain.

Efficient control in long-horizon robotic manipulation is challenging due to complex representation and policy learning requirements. Model-based visual reinforcement learning (RL) has shown great potential in addressing these challenges but still faces notable limitations, particularly in handling sparse rewards and complex visual features in long-horizon environments. To address these limitations, we propose the Recognize-Sense-Plan-Act (RSPA) pipeline for long-horizon tasks and further introduce RoboHorizon, an LLM-assisted multi-view world model tailored for long-horizon robotic manipulation. In RoboHorizon, pre-trained LLMs generate dense reward structures for multi-stage sub-tasks based on task language instructions, enabling robots to better recognize long-horizon tasks. Keyframe discovery is then integrated into the multi-view masked autoencoder (MAE) architecture to enhance the robot's ability to sense critical task sequences, strengthening its multi-stage perception of long-horizon processes. Leveraging these dense rewards and multi-view representations, a robotic world model is constructed to efficiently plan long-horizon tasks, enabling the robot to reliably act through RL algorithms. Experiments on two representative benchmarks, RLBench and FurnitureBench, show that RoboHorizon outperforms state-of-the-art visual model-based RL methods, achieving a 23.35% improvement in task success rates on RLBench's 4 short-horizon tasks and a 29.23% improvement on 6 long-horizon tasks from RLBench and 3 furniture assembly tasks from FurnitureBench.

Intelligent robots need to interact with diverse objects across various environments. The appearance and state of objects frequently undergo complex transformations depending on the object properties, e.g., phase transitions. However, in the vision community, segmenting dynamic objects with phase transitions is overlooked. In light of this, we introduce the concept of phase in segmentation, which categorizes real-world objects based on their visual characteristics and potential morphological and appearance changes. Then, we present a new benchmark, Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation (M$^3$-VOS), to verify the ability of models to understand object phases, which consists of 479 high-resolution videos spanning over 10 distinct everyday scenarios. It provides dense instance mask annotations that capture both object phases and their transitions. We evaluate state-of-the-art methods on M$^3$-VOS, yielding several key insights. Notably, current appearancebased approaches show significant room for improvement when handling objects with phase transitions. The inherent changes in disorder suggest that the predictive performance of the forward entropy-increasing process can be improved through a reverse entropy-reducing process. These findings lead us to propose ReVOS, a new plug-andplay model that improves its performance by reversal refinement. Our data and code will be publicly available at https://zixuan-chen.github.io/M-cubeVOS.github.io/.

Reinforcement learning combined with sim-to-real transfer offers a general framework for developing locomotion controllers for legged robots. To facilitate successful deployment in the real world, smoothing techniques, such as low-pass filters and smoothness rewards, are often employed to develop policies with smooth behaviors. However, because these techniques are non-differentiable and usually require tedious tuning of a large set of hyperparameters, they tend to require extensive manual tuning for each robotic platform. To address this challenge and establish a general technique for enforcing smooth behaviors, we propose a simple and effective method that imposes a Lipschitz constraint on a learned policy, which we refer to as Lipschitz-Constrained Policies (LCP). We show that the Lipschitz constraint can be implemented in the form of a gradient penalty, which provides a differentiable objective that can be easily incorporated with automatic differentiation frameworks. We demonstrate that LCP effectively replaces the need for smoothing rewards or low-pass filters and can be easily integrated into training frameworks for many distinct humanoid robots. We extensively evaluate LCP in both simulation and real-world humanoid robots, producing smooth and robust locomotion controllers. All simulation and deployment code, along with complete checkpoints, is available on our project page: https://lipschitz-constrained-policy.github.io.

Humanoid robots capable of autonomous operation in diverse environments have long been a goal for roboticists. However, autonomous manipulation by humanoid robots has largely been restricted to one specific scene, primarily due to the difficulty of acquiring generalizable skills. Recent advances in 3D visuomotor policies, such as the 3D Diffusion Policy (DP3), have shown promise in extending these capabilities to wilder environments. However, 3D visuomotor policies often rely on camera calibration and point-cloud segmentation, which present challenges for deployment on mobile robots like humanoids. In this work, we introduce the Improved 3D Diffusion Policy (iDP3), a novel 3D visuomotor policy that eliminates these constraints by leveraging egocentric 3D visual representations. We demonstrate that iDP3 enables a full-sized humanoid robot to autonomously perform skills in diverse real-world scenarios, using only data collected in the lab. Videos are available at: https://humanoid-manipulation.github.io

Robots' ability to follow language instructions and execute diverse 3D tasks is vital in robot learning. Traditional imitation learning-based methods perform well on seen tasks but struggle with novel, unseen ones due to variability. Recent approaches leverage large foundation models to assist in understanding novel tasks, thereby mitigating this issue. However, these methods lack a task-specific learning process, which is essential for an accurate understanding of 3D environments, often leading to execution failures. In this paper, we introduce GravMAD, a subgoal-driven, language-conditioned action diffusion framework that combines the strengths of imitation learning and foundation models. Our approach breaks tasks into sub-goals based on language instructions, allowing auxiliary guidance during both training and inference. During training, we introduce Sub-goal Keypose Discovery to identify key sub-goals from demonstrations. Inference differs from training, as there are no demonstrations available, so we use pre-trained foundation models to bridge the gap and identify sub-goals for the current task. In both phases, GravMaps are generated from sub-goals, providing GravMAD with more flexible 3D spatial guidance compared to fixed 3D positions. Empirical evaluations on RLBench show that GravMAD significantly outperforms state-of-the-art methods, with a 28.63% improvement on novel tasks and a 13.36% gain on tasks encountered during training. These results demonstrate GravMAD's strong multi-task learning and generalization in 3D manipulation. Video demonstrations are available at: https://gravmad.github.io. One of the ultimate goals of general-purpose robot manipulation learning is to enable robots to perform a wide range of tasks in real-world 3D environments based on natural language instructions (Hu et al., 2023a). To achieve this, robots must understand task language instructions and align them with the spatial properties of relevant objects in the scene.

We study the problem of mobile manipulation using legged robots equipped with an arm, namely legged loco-manipulation. The robot legs, while usually utilized for mobility, offer an opportunity to amplify the manipulation capabilities by conducting whole-body control. That is, the robot can control the legs and the arm at the same time to extend its workspace. We propose a framework that can conduct the whole-body control autonomously with visual observations. Our approach, namely Visual Whole-Body Control(VBC), is composed of a low-level policy using all degrees of freedom to track the body velocities along with the end-effector position, and a high-level policy proposing the velocities and end-effector position based on visual inputs. We train both levels of policies in simulation and perform Sim2Real transfer for real robot deployment. We perform extensive experiments and show significant improvements over baselines in picking up diverse objects in different configurations (heights, locations, orientations) and environments.

We analyze a general problem in a crowd-sourced setting where one user asks a question (also called item) and other users return answers (also called labels) for this question. Different from existing crowd sourcing work which focuses on finding the most appropriate label for the question (the "truth"), our problem is to determine a ranking of the users based on their ability to answer questions. We call this problem "ability discovery" to emphasize the connection to and duality with the more well-studied problem of "truth discovery". To model items and their labels in a principled way, we draw upon Item Response Theory (IRT) which is the widely accepted theory behind standardized tests such as SAT and GRE. We start from an idealized setting where the relative performance of users is consistent across items and better users choose better fitting labels for each item. We posit that a principled algorithmic solution to our more general problem should solve this ideal setting correctly and observe that the response matrices in this setting obey the Consecutive Ones Property (C1P). While C1P is well understood algorithmically with various discrete algorithms, we devise a novel variant of the HITS algorithm which we call "HITSNDIFFS" (or HND), and prove that it can recover the ideal C1P-permutation in case it exists. Unlike fast combinatorial algorithms for finding the consecutive ones permutation (if it exists), HND also returns an ordering when such a permutation does not exist. Thus it provides a principled heuristic for our problem that is guaranteed to return the correct answer in the ideal setting. Our experiments show that HND produces user rankings with robustly high accuracy compared to state-of-the-art truth discovery methods. We also show that our novel variant of HITS scales better in the number of users than ABH, the only prior spectral C1P reconstruction algorithm.

Numerous approaches have attempted to interpret deep neural networks (DNNs) by attributing the prediction of DNN to its input features. One of the well-studied attribution methods is Integrated Gradients (IG). Specifically, the choice of baselines for IG is a critical consideration for generating meaningful and unbiased explanations for model predictions in different scenarios. However, current practice of exploiting a single baseline fails to fulfill this ambition, thus demanding multiple baselines. Fortunately, the inherent connection between IG and Aumann-Shapley Value forms a unique perspective to rethink the design of baselines. Under certain hypothesis, we theoretically analyse that a set of baseline aligns with the coalitions in Shapley Value. Thus, we propose a novel baseline construction method called Shapley Integrated Gradients (SIG) that searches for a set of baselines by proportional sampling to partly simulate the computation path of Shapley Value. Simulations on GridWorld show that SIG approximates the proportion of Shapley Values. Furthermore, experiments conducted on various image tasks demonstrate that compared to IG using other baseline methods, SIG exhibits an improved estimation of feature's contribution, offers more consistent explanations across diverse applications, and is generic to distinct data types or instances with insignificant computational overhead.