Jianyu Chen

Xinyang Gu, Yen-Jen Wang, Xiang Zhu et al.

Humanoid robots, with their human-like skeletal structure, are especially suited for tasks in human-centric environments. However, this structure is accompanied by additional challenges in locomotion controller design, especially in complex real-world environments. As a result, existing humanoid robots are limited to relatively simple terrains, either with model-based control or model-free reinforcement learning. In this work, we introduce Denoising World Model Learning (DWL), an end-to-end reinforcement learning framework for humanoid locomotion control, which demonstrates the world's first humanoid robot to master real-world challenging terrains such as snowy and inclined land in the wild, up and down stairs, and extremely uneven terrains. All scenarios run the same learned neural network with zero-shot sim-to-real transfer, indicating the superior robustness and generalization capability of the proposed method.

Jianke Zhang, Yanjiang Guo, Xiaoyu Chen et al.

Large Vision-Language-Action (VLA) models, leveraging powerful pre trained Vision-Language Models (VLMs) backends, have shown promise in robotic control due to their impressive generalization ability. However, the success comes at a cost. Their reliance on VLM backends with billions of parameters leads to high computational costs and inference latency, limiting the testing scenarios to mainly quasi-static tasks and hindering performance in dynamic tasks requiring rapid interactions. To address these limitations, this paper proposes HiRT, a Hierarchical Robot Transformer framework that enables flexible frequency and performance trade-off. HiRT keeps VLMs running at low frequencies to capture temporarily invariant features while enabling real-time interaction through a high-frequency vision-based policy guided by the slowly updated features. Experiment results in both simulation and real-world settings demonstrate significant improvements over baseline methods. Empirically, in static tasks, we double the control frequency and achieve comparable success rates. Additionally, on novel real-world dynamic ma nipulation tasks which are challenging for previous VLA models, HiRT improves the success rate from 48% to 75%.

Yuheng Lei, Jianyu Chen, Shengbo Eben Li et al.

Choosing an appropriate parameter set for the designed controller is critical for the final performance but usually requires a tedious and careful tuning process, which implies a strong need for automatic tuning methods. However, among existing methods, derivative-free ones suffer from poor scalability or low efficiency, while gradient-based ones are often unavailable due to possibly non-differentiable controller structure. To resolve the issues, we tackle the controller tuning problem using a novel derivative-free reinforcement learning (RL) framework, which performs timestep-wise perturbation in parameter space during experience collection and integrates derivative-free policy updates into the advanced actor-critic RL architecture to achieve high versatility and efficiency. To demonstrate the framework's efficacy, we conduct numerical experiments on two concrete examples from autonomous driving, namely, adaptive cruise control with PID controller and trajectory tracking with MPC controller. Experimental results show that the proposed method outperforms popular baselines and highlight its strong potential for controller tuning.

Yanjiang Guo, Zheyuan Jiang, Yen-Jen Wang et al.

Reinforcement learning (RL) has achieved remarkable success in complex robotic systems (eg. quadruped locomotion). In previous works, the RL-based controller was typically implemented as a single neural network with concatenated observation input. However, the corresponding learned policy is highly task-specific. Since all motors are controlled in a centralized way, out-of-distribution local observations can impact global motors through the single coupled neural network policy. In contrast, animals and humans can control their limbs separately. Inspired by this biological phenomenon, we propose a Decentralized motor skill (DEMOS) learning algorithm to automatically discover motor groups that can be decoupled from each other while preserving essential connections and then learn a decentralized motor control policy. Our method improves the robustness and generalization of the policy without sacrificing performance. Experiments on quadruped and humanoid robots demonstrate that the learned policy is robust against local motor malfunctions and can be transferred to new tasks.

Yikai Wang, Zheyuan Jiang, Jianyu Chen

Recently, reinforcement learning has become a promising and polular solution for robot legged locomotion. Compared to model-based control, reinforcement learning based controllers can achieve better robustness against uncertainties of environments through sim-to-real learning. However, the corresponding learned gaits are in general overly conservative and unatural. In this paper, we propose a new framework for learning robust, agile and natural legged locomotion skills over challenging terrain. We incorporate an adversarial training branch based on real animal locomotion data upon a teacher-student training pipeline for robust sim-to-real transfer. Empirical results on both simulation and real world of a quadruped robot demonstrate that our proposed algorithm enables robustly traversing challenging terrains such as stairs, rocky ground and slippery floor with only proprioceptive perception. Meanwhile, the gaits are more agile, natural, and energy efficient compared to the baselines. Both qualitative and quantitative results are presented in this paper.

Xinyang Gu, Yen-Jen Wang, Jianyu Chen

Humanoid-Gym is an easy-to-use reinforcement learning (RL) framework based on Nvidia Isaac Gym, designed to train locomotion skills for humanoid robots, emphasizing zero-shot transfer from simulation to the real-world environment. Humanoid-Gym also integrates a sim-to-sim framework from Isaac Gym to Mujoco that allows users to verify the trained policies in different physical simulations to ensure the robustness and generalization of the policies. This framework is verified by RobotEra's XBot-S (1.2-meter tall humanoid robot) and XBot-L (1.65-meter tall humanoid robot) in a real-world environment with zero-shot sim-to-real transfer. The project website and source code can be found at: https://sites.google.com/view/humanoid-gym/.

Yucheng Hu, Yanjiang Guo, Pengchao Wang et al.

Visual representations play a crucial role in developing generalist robotic policies. Previous vision encoders, typically pre-trained with single-image reconstruction or two-image contrastive learning, tend to capture static information, often neglecting the dynamic aspects vital for embodied tasks. Recently, video diffusion models (VDMs) demonstrate the ability to predict future frames and showcase a strong understanding of physical world. We hypothesize that VDMs inherently produce visual representations that encompass both current static information and predicted future dynamics, thereby providing valuable guidance for robot action learning. Based on this hypothesis, we propose the Video Prediction Policy (VPP), which learns implicit inverse dynamics model conditioned on predicted future representations inside VDMs. To predict more precise future, we fine-tune pre-trained video foundation model on robot datasets along with internet human manipulation data. In experiments, VPP achieves a 18.6\% relative improvement on the Calvin ABC-D generalization benchmark compared to the previous state-of-the-art, and demonstrates a 31.6\% increase in success rates for complex real-world dexterous manipulation tasks. Project page at https://video-prediction-policy.github.io

Yanjiang Guo, Jianke Zhang, Xiaoyu Chen et al.

Recent studies have successfully integrated large vision-language models (VLMs) into low-level robotic control by supervised fine-tuning (SFT) with expert robotic datasets, resulting in what we term vision-language-action (VLA) models. Although the VLA models are powerful, how to improve these large models during interaction with environments remains an open question. In this paper, we explore how to further improve these VLA models via Reinforcement Learning (RL), a commonly used fine-tuning technique for large models. However, we find that directly applying online RL to large VLA models presents significant challenges, including training instability that severely impacts the performance of large models, and computing burdens that exceed the capabilities of most local machines. To address these challenges, we propose iRe-VLA framework, which iterates between Reinforcement Learning and Supervised Learning to effectively improve VLA models, leveraging the exploratory benefits of RL while maintaining the stability of supervised learning. Experiments in two simulated benchmarks and a real-world manipulation suite validate the effectiveness of our method.

Yanjiang Guo, Yucheng Hu, Jianke Zhang et al.

Diffusion models have demonstrated remarkable capabilities in image generation tasks, including image editing and video creation, representing a good understanding of the physical world. On the other line, diffusion models have also shown promise in robotic control tasks by denoising actions, known as diffusion policy. Although the diffusion generative model and diffusion policy exhibit distinct capabilities--image prediction and robotic action, respectively--they technically follow a similar denoising process. In robotic tasks, the ability to predict future images and generate actions is highly correlated since they share the same underlying dynamics of the physical world. Building on this insight, we introduce PAD, a novel visual policy learning framework that unifies image Prediction and robot Action within a joint Denoising process. Specifically, PAD utilizes Diffusion Transformers (DiT) to seamlessly integrate images and robot states, enabling the simultaneous prediction of future images and robot actions. Additionally, PAD supports co-training on both robotic demonstrations and large-scale video datasets and can be easily extended to other robotic modalities, such as depth images. PAD outperforms previous methods, achieving a significant 26.3% relative improvement on the full Metaworld benchmark, by utilizing a single text-conditioned visual policy within a data-efficient imitation learning setting. Furthermore, PAD demonstrates superior generalization to unseen tasks in real-world robot manipulation settings with 28.0% success rate increase compared to the strongest baseline. Project page at https://sites.google.com/view/pad-paper

Xiaoyu Chen, Hangxing Wei, Pushi Zhang et al.

Vision-Language-Action (VLA) models have emerged as a popular paradigm for learning robot manipulation policies that can follow language instructions and generalize to novel scenarios. Recent works have begun to explore the incorporation of latent actions, abstract representations of motion between two frames, into VLA pre-training. In this paper, we introduce villa-X, a novel Vision-Language-Latent-Action (ViLLA) framework that advances latent action modeling for learning generalizable robot manipulation policies. Our approach improves both how latent actions are learned and how they are incorporated into VLA pre-training. We demonstrate that villa-X can generate latent action plans in a zero-shot fashion, even for unseen embodiments and open-vocabulary symbolic understanding. This capability enables villa-X to achieve superior performance across diverse simulation tasks in SIMPLER and on two real-world robotic setups involving both gripper and dexterous hand manipulation. These results establish villa-X as a principled and scalable paradigm for learning generalizable robot manipulation policies. We believe it provides a strong foundation for future research.

Xinghao Zhu, Yefan Zhou, Yongxiang Fan et al.

Robotic grasping for a diverse set of objects is essential in many robot manipulation tasks. One promising approach is to learn deep grasping models from large training datasets of object images and grasp labels. However, empirical grasping datasets are typically sparsely labeled (i.e., a small number of successful grasp labels in each image). The data sparsity issue can lead to insufficient supervision and false-negative labels and thus results in poor learning results. This paper proposes a Maximum Likelihood Grasp Sampling Loss (MLGSL) to tackle the data sparsity issue. The proposed method supposes that successful grasps are stochastically sampled from the predicted grasp distribution and maximizes the observing likelihood. MLGSL is utilized for training a fully convolutional network that generates thousands of grasps simultaneously. Training results suggest that models based on MLGSL can learn to grasp with datasets composing of 2 labels per image. Compared to previous works, which require training datasets of 16 labels per image, MLGSL is 8x more data-efficient. Meanwhile, physical robot experiments demonstrate an equivalent performance at a 90.7% grasp success rate on household objects.

Haitong Ma, Yang Guan, Shegnbo Eben Li et al.

The safety constraints commonly used by existing safe reinforcement learning (RL) methods are defined only on expectation of initial states, but allow each certain state to be unsafe, which is unsatisfying for real-world safety-critical tasks. In this paper, we introduce the feasible actor-critic (FAC) algorithm, which is the first model-free constrained RL method that considers statewise safety, e.g, safety for each initial state. We claim that some states are inherently unsafe no matter what policy we choose, while for other states there exist policies ensuring safety, where we say such states and policies are feasible. By constructing a statewise Lagrange function available on RL sampling and adopting an additional neural network to approximate the statewise Lagrange multiplier, we manage to obtain the optimal feasible policy which ensures safety for each feasible state and the safest possible policy for infeasible states. Furthermore, the trained multiplier net can indicate whether a given state is feasible or not through the statewise complementary slackness condition. We provide theoretical guarantees that FAC outperforms previous expectation-based constrained RL methods in terms of both constraint satisfaction and reward optimization. Experimental results on both robot locomotive tasks and safe exploration tasks verify the safety enhancement and feasibility interpretation of the proposed method.

Yang Guan, Jingliang Duan, Shengbo Eben Li et al.

Reinforcement learning (RL) shows great potential in sequential decision-making. At present, mainstream RL algorithms are data-driven, which usually yield better asymptotic performance but much slower convergence compared with model-driven methods. This paper proposes mixed policy gradient (MPG) algorithm, which fuses the empirical data and the transition model in policy gradient (PG) to accelerate convergence without performance degradation. Formally, MPG is constructed as a weighted average of the data-driven and model-driven PGs, where the former is the derivative of the learned Q-value function, and the latter is that of the model-predictive return. To guide the weight design, we analyze and compare the upper bound of each PG error. Relying on that, a rule-based method is employed to heuristically adjust the weights. In particular, to get a better PG, the weight of the data-driven PG is designed to grow along the learning process while the other to decrease. Simulation results show that the MPG method achieves the best asymptotic performance and convergence speed compared with other baseline algorithms.

Baiyu Peng, Yao Mu, Jingliang Duan et al.

Safety is essential for reinforcement learning (RL) applied in real-world tasks like autonomous driving. Chance constraints which guarantee the satisfaction of state constraints at a high probability are suitable to represent the requirements in real-world environment with uncertainty. Existing chance constrained RL methods like the penalty method and the Lagrangian method either exhibit periodic oscillations or cannot satisfy the constraints. In this paper, we address these shortcomings by proposing a separated proportional-integral Lagrangian (SPIL) algorithm. Taking a control perspective, we first interpret the penalty method and the Lagrangian method as proportional feedback and integral feedback control, respectively. Then, a proportional-integral Lagrangian method is proposed to steady learning process while improving safety. To prevent integral overshooting and reduce conservatism, we introduce the integral separation technique inspired by PID control. Finally, an analytical gradient of the chance constraint is utilized for model-based policy optimization. The effectiveness of SPIL is demonstrated by a narrow car-following task. Experiments indicate that compared with previous methods, SPIL improves the performance while guaranteeing safety, with a steady learning process.

Zhuo Xu, Jianyu Chen, Masayoshi Tomizuka

In this paper, we continue our prior work on using imitation learning (IL) and model free reinforcement learning (RL) to learn driving policies for autonomous driving in urban scenarios, by introducing a model based RL method to drive the autonomous vehicle in the Carla urban driving simulator. Although IL and model free RL methods have been proved to be capable of solving lots of challenging tasks, including playing video games, robots, and, in our prior work, urban driving, the low sample efficiency of such methods greatly limits their applications on actual autonomous driving. In this work, we developed a model based RL algorithm of guided policy search (GPS) for urban driving tasks. The algorithm iteratively learns a parameterized dynamic model to approximate the complex and interactive driving task, and optimizes the driving policy under the nonlinear approximate dynamic model. As a model based RL approach, when applied in urban autonomous driving, the GPS has the advantages of higher sample efficiency, better interpretability, and greater stability. We provide extensive experiments validating the effectiveness of the proposed method to learn robust driving policy for urban driving in Carla. We also compare the proposed method with other policy search and model free RL baselines, showing 100x better sample efficiency of the GPS based RL method, and also that the GPS based method can learn policies for harder tasks that the baseline methods can hardly learn.

Jianyu Chen, Zhuo Xu, Masayoshi Tomizuka

Current autonomous driving systems are composed of a perception system and a decision system. Both of them are divided into multiple subsystems built up with lots of human heuristics. An end-to-end approach might clean up the system and avoid huge efforts of human engineering, as well as obtain better performance with increasing data and computation resources. Compared to the decision system, the perception system is more suitable to be designed in an end-to-end framework, since it does not require online driving exploration. In this paper, we propose a novel end-to-end approach for autonomous driving perception. A latent space is introduced to capture all relevant features useful for perception, which is learned through sequential latent representation learning. The learned end-to-end perception model is able to solve the detection, tracking, localization and mapping problems altogether with only minimum human engineering efforts and without storing any maps online. The proposed method is evaluated in a realistic urban driving simulator, with both camera image and lidar point cloud as sensor inputs. The codes and videos of this work are available at our github repo and project website.

Jianyu Chen, Bodi Yuan, Masayoshi Tomizuka

The decision and planning system for autonomous driving in urban environments is hard to design. Most current methods manually design the driving policy, which can be expensive to develop and maintain at scale. Instead, with imitation learning we only need to collect data and the computer will learn and improve the driving policy automatically. However, existing imitation learning methods for autonomous driving are hardly performing well for complex urban scenarios. Moreover, the safety is not guaranteed when we use a deep neural network policy. In this paper, we proposed a framework to learn the driving policy in urban scenarios efficiently given offline connected driving data, with a safety controller incorporated to guarantee safety at test time. The experiments show that our method can achieve high performance in realistic simulations of urban driving scenarios.