arXiv subjects

Zhaoming Xie

Publications and source records attributed to Zhaoming Xie.

17 recordsLinked to original sources

arXiv2026

Efficient Sim-to-Real Transfer of World-Action Models from Synthetic Priors

Bridging the sim-to-real gap is a core challenge in deploying learned manipulation policies. Sim-to-real learning is attractive because it can replace expensive real robot demonstrations with scalable synthetic data, yet world-action models have not previously been shown to transfer from simulation to real robotic manipulation. We study whether a world-action model can be trained from synthetic priors and deployed zero-shot in the real world. To this end, we build upon Cosmos Policy, a video diffusion model adapted for visuomotor control. We construct simulation environments with extensive domain randomization and generate demonstrations using the AnyTask motion planning pipeline. We evaluate our approach across object lifting, drawer opening, and pick-and-place tasks using ${\sim}800$ synthetic demonstrations per task and no real demonstrations. When deployed zero-shot on a Franka Robot, our policy attains a 35\% average success rate. To our knowledge, this represents the first successful sim-to-real transfer of a world-action model for robotic manipulation.

cs.RO↗

arXiv2026

Learning Smooth Time-Varying Linear Policies with an Action Jacobian Penalty

Reinforcement learning provides a framework for learning control policies that can reproduce diverse motions for simulated characters. However, such policies often exploit unnatural high-frequency signals that are unachievable by humans or physical robots, making them poor representations of real-world behaviors. Existing work addresses this issue by adding a reward term that penalizes a large change in actions over time. This term often requires substantial tuning efforts. We propose to use the action Jacobian penalty, which penalizes changes in action with respect to the changes in simulated state directly through auto differentiation. This effectively eliminates unrealistic high-frequency control signals without task specific tuning. While effective, the action Jacobian penalty introduces significant computational overhead when used with traditional fully connected neural network architectures. To mitigate this, we introduce a new architecture called a Linear Policy Net (LPN) that significantly reduces the computational burden for calculating the action Jacobian penalty during training. In addition, a LPN requires no parameter tuning, exhibits faster learning convergence compared to baseline methods, and can be more efficiently queried during inference time compared to a fully connected neural network. We demonstrate that a Linear Policy Net, combined with the action Jacobian penalty, is able to learn policies that generate smooth signals while solving a number of motion imitation tasks with different characteristics, including dynamic motions such as a backflip and various challenging parkour skills. Finally, we apply this approach to create policies for dynamic motions on a physical quadrupedal robot equipped with an arm.

cs.RO↗

arXiv2025

Whole Body Model Predictive Control for Spin-Aware Quadrupedal Table Tennis

Developing table tennis robots that mirror human speed, accuracy, and ability to predict and respond to the full range of ball spins remains a significant challenge for legged robots. To demonstrate these capabilities we present a system to play dynamic table tennis for quadrupedal robots that integrates high speed perception, trajectory prediction, and agile control. Our system uses external cameras for high-speed ball localization, physical models with learned residuals to infer spin and predict trajectories, and a novel model predictive control (MPC) formulation for agile full-body control. Notably, a continuous set of stroke strategies emerge automatically from different ball return objectives using this control paradigm. We demonstrate our system in the real world on a Spot quadruped, evaluate accuracy of each system component, and exhibit coordination through the system's ability to aim and return balls with varying spin types. As a further demonstration, the system is able to rally with human players.

cs.RO↗

arXiv2025

Humanoid Locomotion and Manipulation: Current Progress and Challenges in Control, Planning, and Learning

Humanoid robots hold great potential to perform various human-level skills, involving unified locomotion and manipulation in real-world settings. Driven by advances in machine learning and the strength of existing model-based approaches, these capabilities have progressed rapidly, but often separately. This survey offers a comprehensive overview of the state-of-the-art in humanoid locomotion and manipulation (HLM), with a focus on control, planning, and learning methods. We first review the model-based methods that have been the backbone of humanoid robotics for the past three decades. We discuss contact planning, motion planning, and whole-body control, highlighting the trade-offs between model fidelity and computational efficiency. Then the focus is shifted to examine emerging learning-based methods, with an emphasis on reinforcement and imitation learning that enhance the robustness and versatility of loco-manipulation skills. Furthermore, we assess the potential of integrating foundation models with humanoid embodiments to enable the development of generalist humanoid agents. This survey also highlights the emerging role of tactile sensing, particularly whole-body tactile feedback, as a crucial modality for handling contact-rich interactions. Finally, we compare the strengths and limitations of model-based and learning-based paradigms from multiple perspectives, such as robustness, computational efficiency, versatility, and generalizability, and suggest potential solutions to existing challenges.

cs.RO↗

arXiv2025

Robust Humanoid Walking on Compliant and Uneven Terrain with Deep Reinforcement Learning

For the deployment of legged robots in real-world environments, it is essential to develop robust locomotion control methods for challenging terrains that may exhibit unexpected deformability and irregularity. In this paper, we explore the application of sim-to-real deep reinforcement learning (RL) for the design of bipedal locomotion controllers for humanoid robots on compliant and uneven terrains. Our key contribution is to show that a simple training curriculum for exposing the RL agent to randomized terrains in simulation can achieve robust walking on a real humanoid robot using only proprioceptive feedback. We train an end-to-end bipedal locomotion policy using the proposed approach, and show extensive real-robot demonstration on the HRP-5P humanoid over several difficult terrains inside and outside the lab environment. Further, we argue that the robustness of a bipedal walking policy can be improved if the robot is allowed to exhibit aperiodic motion with variable stepping frequency. We propose a new control policy to enable modification of the observed clock signal, leading to adaptive gait frequencies depending on the terrain and command velocity. Through simulation experiments, we show the effectiveness of this policy specifically for walking over challenging terrains by controlling swing and stance durations. The code for training and evaluation is available online at https://github.com/rohanpsingh/LearningHumanoidWalking. Demo video is available at https://www.youtube.com/watch?v=ZgfNzGAkk2Q.

cs.RO↗

arXiv2024

PDP: Physics-Based Character Animation via Diffusion Policy

Generating diverse and realistic human motion that can physically interact with an environment remains a challenging research area in character animation. Meanwhile, diffusion-based methods, as proposed by the robotics community, have demonstrated the ability to capture highly diverse and multi-modal skills. However, naively training a diffusion policy often results in unstable motions for high-frequency, under-actuated control tasks like bipedal locomotion due to rapidly accumulating compounding errors, pushing the agent away from optimal training trajectories. The key idea lies in using RL policies not just for providing optimal trajectories but for providing corrective actions in sub-optimal states, giving the policy a chance to correct for errors caused by environmental stimulus, model errors, or numerical errors in simulation. Our method, Physics-Based Character Animation via Diffusion Policy (PDP), combines reinforcement learning (RL) and behavior cloning (BC) to create a robust diffusion policy for physics-based character animation. We demonstrate PDP on perturbation recovery, universal motion tracking, and physics-based text-to-motion synthesis.

cs.GR↗

arXiv2024

Learning-based legged locomotion; state of the art and future perspectives

Legged locomotion holds the premise of universal mobility, a critical capability for many real-world robotic applications. Both model-based and learning-based approaches have advanced the field of legged locomotion in the past three decades. In recent years, however, a number of factors have dramatically accelerated progress in learning-based methods, including the rise of deep learning, rapid progress in simulating robotic systems, and the availability of high-performance and affordable hardware. This article aims to give a brief history of the field, to summarize recent efforts in learning locomotion skills for quadrupeds, and to provide researchers new to the area with an understanding of the key issues involved. With the recent proliferation of humanoid robots, we further outline the rapid rise of analogous methods for bipedal locomotion. We conclude with a discussion of open problems as well as related societal impact.

cs.RO↗

arXiv2023

Learning Bipedal Walking for Humanoids with Current Feedback

Recent advances in deep reinforcement learning (RL) based techniques combined with training in simulation have offered a new approach to developing robust controllers for legged robots. However, the application of such approaches to real hardware has largely been limited to quadrupedal robots with direct-drive actuators and light-weight bipedal robots with low gear-ratio transmission systems. Application to real, life-sized humanoid robots has been less common arguably due to a large sim2real gap. In this paper, we present an approach for effectively overcoming the sim2real gap issue for humanoid robots arising from inaccurate torque-tracking at the actuator level. Our key idea is to utilize the current feedback from the actuators on the real robot, after training the policy in a simulation environment artificially degraded with poor torque-tracking. Our approach successfully trains a unified, end-to-end policy in simulation that can be deployed on a real HRP-5P humanoid robot to achieve bipedal locomotion. Through ablations, we also show that a feedforward policy architecture combined with targeted dynamics randomization is sufficient for zero-shot sim2real success, thus eliminating the need for computationally expensive, memory-based network architectures. Finally, we validate the robustness of the proposed RL policy by comparing its performance against a conventional model-based controller for walking on uneven terrain with the real robot.

cs.RO↗

arXiv2023

Hierarchical Planning and Control for Box Loco-Manipulation

Humans perform everyday tasks using a combination of locomotion and manipulation skills. Building a system that can handle both skills is essential to creating virtual humans. We present a physically-simulated human capable of solving box rearrangement tasks, which requires a combination of both skills. We propose a hierarchical control architecture, where each level solves the task at a different level of abstraction, and the result is a physics-based simulated virtual human capable of rearranging boxes in a cluttered environment. The control architecture integrates a planner, diffusion models, and physics-based motion imitation of sparse motion clips using deep reinforcement learning. Boxes can vary in size, weight, shape, and placement height. Code and trained control policies are provided.

cs.RO↗

arXiv2023

OPT-Mimic: Imitation of Optimized Trajectories for Dynamic Quadruped Behaviors

Reinforcement Learning (RL) has seen many recent successes for quadruped robot control. The imitation of reference motions provides a simple and powerful prior for guiding solutions towards desired solutions without the need for meticulous reward design. While much work uses motion capture data or hand-crafted trajectories as the reference motion, relatively little work has explored the use of reference motions coming from model-based trajectory optimization. In this work, we investigate several design considerations that arise with such a framework, as demonstrated through four dynamic behaviours: trot, front hop, 180 backflip, and biped stepping. These are trained in simulation and transferred to a physical Solo 8 quadruped robot without further adaptation. In particular, we explore the space of feed-forward designs afforded by the trajectory optimizer to understand its impact on RL learning efficiency and sim-to-real transfer. These findings contribute to the long standing goal of producing robot controllers that combine the interpretability and precision of model-based optimization with the robustness that model-free RL-based controllers offer.

cs.RO↗

arXiv2022

GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model

Model-free reinforcement learning (RL) for legged locomotion commonly relies on a physics simulator that can accurately predict the behaviors of every degree of freedom of the robot. In contrast, approximate reduced-order models are commonly used for many model predictive control strategies. In this work we abandon the conventional use of high-fidelity dynamics models in RL and we instead seek to understand what can be achieved when using RL with a much simpler centroidal model when applied to quadrupedal locomotion. We show that RL-based control of the accelerations of a centroidal model is surprisingly effective, when combined with a quadratic program to realize the commanded actions via ground contact forces. It allows for a simple reward structure, reduced computational costs, and robust sim-to-real transfer. We show the generality of the method by demonstrating flat-terrain gaits, stepping-stone locomotion, two-legged in-place balance, balance beam locomotion, and direct sim-to-real transfer.

cs.RO↗

arXiv2021

Dynamics Randomization Revisited:A Case Study for Quadrupedal Locomotion

Understanding the gap between simulation and reality is critical for reinforcement learning with legged robots, which are largely trained in simulation. However, recent work has resulted in sometimes conflicting conclusions with regard to which factors are important for success, including the role of dynamics randomization. In this paper, we aim to provide clarity and understanding on the role of dynamics randomization in learning robust locomotion policies for the Laikago quadruped robot. Surprisingly, in contrast to prior work with the same robot model, we find that direct sim-to-real transfer is possible without dynamics randomization or on-robot adaptation schemes. We conduct extensive ablation studies in a sim-to-sim setting to understand the key issues underlying successful policy transfer, including other design decisions that can impact policy robustness. We further ground our conclusions via sim-to-real experiments with various gaits, speeds, and stepping frequencies. Additional Details: https://www.pair.toronto.edu/understanding-dr/.

cs.RO↗

arXiv2020

Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotion

We present a hierarchical framework that combines model-based control and reinforcement learning (RL) to synthesize robust controllers for a quadruped (the Unitree Laikago). The system consists of a high-level controller that learns to choose from a set of primitives in response to changes in the environment and a low-level controller that utilizes an established control method to robustly execute the primitives. Our framework learns a controller that can adapt to challenging environmental changes on the fly, including novel scenarios not seen during training. The learned controller is up to 85~percent more energy efficient and is more robust compared to baseline methods. We also deploy the controller on a physical robot without any randomization or adaptation scheme.

cs.RO↗

arXiv2020

ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills

Humans are highly adept at walking in environments with foot placement constraints, including stepping-stone scenarios where the footstep locations are fully constrained. Finding good solutions to stepping-stone locomotion is a longstanding and fundamental challenge for animation and robotics. We present fully learned solutions to this difficult problem using reinforcement learning. We demonstrate the importance of a curriculum for efficient learning and evaluate four possible curriculum choices compared to a non-curriculum baseline. Results are presented for a simulated human character, a realistic bipedal robot simulation and a monster character, in each case producing robust, plausible motions for challenging stepping stone sequences and terrains.

cs.GR↗

arXiv2020

Learning to Correspond Dynamical Systems

Many dynamical systems exhibit similar structure, as often captured by hand-designed simplified models that can be used for analysis and control. We develop a method for learning to correspond pairs of dynamical systems via a learned latent dynamical system. Given trajectory data from two dynamical systems, we learn a shared latent state space and a shared latent dynamics model, along with an encoder-decoder pair for each of the original systems. With the learned correspondences in place, we can use a simulation of one system to produce an imagined motion of its counterpart. We can also simulate in the learned latent dynamics and synthesize the motions of both corresponding systems, as a form of bisimulation. We demonstrate the approach using pairs of controlled bipedal walkers, as well as by pairing a walker with a controlled pendulum.

cs.LG↗

arXiv2019

Iterative Reinforcement Learning Based Design of Dynamic Locomotion Skills for Cassie

Deep reinforcement learning (DRL) is a promising approach for developing legged locomotion skills. However, the iterative design process that is inevitable in practice is poorly supported by the default methodology. It is difficult to predict the outcomes of changes made to the reward functions, policy architectures, and the set of tasks being trained on. In this paper, we propose a practical method that allows the reward function to be fully redefined on each successive design iteration while limiting the deviation from the previous iteration. We characterize policies via sets of Deterministic Action Stochastic State (DASS) tuples, which represent the deterministic policy state-action pairs as sampled from the states visited by the trained stochastic policy. New policies are trained using a policy gradient algorithm which then mixes RL-based policy gradients with gradient updates defined by the DASS tuples. The tuples also allow for robust policy distillation to new network architectures. We demonstrate the effectiveness of this iterative-design approach on the bipedal robot Cassie, achieving stable walking with different gait styles at various speeds. We demonstrate the successful transfer of policies learned in simulation to the physical robot without any dynamics randomization, and that variable-speed walking policies for the physical robot can be represented by a small dataset of 5-10k tuples.

cs.RO↗

arXiv2018

Feedback Control For Cassie With Deep Reinforcement Learning

Bipedal locomotion skills are challenging to develop. Control strategies often use local linearization of the dynamics in conjunction with reduced-order abstractions to yield tractable solutions. In these model-based control strategies, the controller is often not fully aware of many details, including torque limits, joint limits, and other non-linearities that are necessarily excluded from the control computations for simplicity. Deep reinforcement learning (DRL) offers a promising model-free approach for controlling bipedal locomotion which can more fully exploit the dynamics. However, current results in the machine learning literature are often based on ad-hoc simulation models that are not based on corresponding hardware. Thus it remains unclear how well DRL will succeed on realizable bipedal robots. In this paper, we demonstrate the effectiveness of DRL using a realistic model of Cassie, a bipedal robot. By formulating a feedback control problem as finding the optimal policy for a Markov Decision Process, we are able to learn robust walking controllers that imitate a reference motion with DRL. Controllers for different walking speeds are learned by imitating simple time-scaled versions of the original reference motion. Controller robustness is demonstrated through several challenging tests, including sensory delay, walking blindly on irregular terrain and unexpected pushes at the pelvis. We also show we can interpolate between individual policies and that robustness can be improved with an interpolated policy.

cs.RO↗