arXiv subjects

Zishang Zhang

Publications and source records attributed to Zishang Zhang.

4 recordsLinked to original sources

arXiv2026

asRoBallet: Closing the Sim2Real Gap via Friction-Aware Reinforcement Learning for Underactuated Spherical Dynamics

We introduce asRoBallet, to the best of our knowledge, the first end-to-end reinforcement learning (RL) locomotion policy deployed on a humanoid ballbot hardware platform. Historically, ballbots have served as a canonical benchmark for underactuated and nonholonomic control, which are characterized by a reality gap in complex friction models for wheel-ball-floor interactions. While current literature demonstrates successful handling of 3D balancing with LQR and MPC, transitioning to actual hardware for a humanoid ballbot using RL is currently hindered by critical gaps in contact modeling, actuator latency & jitter, and safe hardware exploration. This study proposes a high-fidelity MuJoCo simulation that explicitly models the discrete roller mechanics of ETH-type omni-wheels, thereby capturing parasitic vibrations and contact discontinuities that have previously been ignored. We also developed a Friction-Aware Reinforcement Learning framework that achieves zero-shot Sim2Real transfer by mastering the coupled rolling, lateral, and torsional friction channels at the wheel-ball and ball-floor interfaces. We designed asRoBallet through subtractive reconfiguration, repurposing key components from an overconstrained quadruped and integrating them into a newly designed structural frame to achieve a robust research platform at low cost. We also developed a generalized iOS ecosystem that transforms consumer electronics into a low-latency interface, enabling a single operator to orchestrate expressive humanoid maneuvers via intuitive natural motion.

cs.RO↗

arXiv2025

MagiClaw: A Dual-Use, Vision-Based Soft Gripper for Bridging the Human Demonstration to Robotic Deployment Gap

The transfer of manipulation skills from human demonstration to robotic execution is often hindered by a "domain gap" in sensing and morphology. This paper introduces MagiClaw, a versatile two-finger end-effector designed to bridge this gap. MagiClaw functions interchangeably as both a handheld tool for intuitive data collection and a robotic end-effector for policy deployment, ensuring hardware consistency and reliability. Each finger incorporates a Soft Polyhedral Network (SPN) with an embedded camera, enabling vision-based estimation of 6-DoF forces and contact deformation. This proprioceptive data is fused with exteroceptive environmental sensing from an integrated iPhone, which provides 6D pose, RGB video, and LiDAR-based depth maps. Through a custom iOS application, MagiClaw streams synchronized, multi-modal data for real-time teleoperation, offline policy learning, and immersive control via mixed-reality interfaces. We demonstrate how this unified system architecture lowers the barrier to collecting high-fidelity, contact-rich datasets and accelerates the development of generalizable manipulation policies. Please refer to the iOS app at https://apps.apple.com/cn/app/magiclaw/id6661033548 for further details.

cs.RO↗

arXiv2024

Overconstrained Locomotion

This paper studies the design, control, and learning of a novel robotic limb that produces overconstrained locomotion by employing the Bennett linkage for motion generation, capable of parametric reconfiguration between a reptile- and mammal-inspired morphology within a single quadruped. In contrast to the prevailing focus on planar linkages, this research delves into adopting overconstrained linkages as the limb mechanism. The overconstrained linkages have solid theoretical foundations in advanced kinematics but are under-explored in robotic applications. This study showcases the morphological superiority of Overconstrained Robotic Limbs (ORLs) that can transform into planar or spherical limbs, exemplified using the simplest case of a Bennett linkage as an ORL. We apply Model Predictive Control (MPC) to simulate a range of overconstrained locomotion tasks, revealing its superiority in energy efficiency against planar limbs when considering foothold distances and speeds. The results are further verified in overconstrained locomotion policies optimized from Reinforcement Learning (RL). From an evolutionary biology perspective, these findings highlight the mechanism distinctions in limb design between reptiles and mammals and represent the first documented instance of ORLs outperforming planar limb designs in dynamic locomotion. Future studies will focus on deploying the model-based and learning-based overconstrained locomotion skills in the robotic hardware to close the Sim2Real gap for developing evolutionary-inspired, energy-efficient control of novel robotic limbs.

cs.RO↗

arXiv2024

Evolutionary Morphology Towards Overconstrained Locomotion via Large-Scale, Multi-Terrain Deep Reinforcement Learning

While the animals' Fin-to-Limb evolution has been well-researched in biology, such morphological transformation remains under-adopted in the modern design of advanced robotic limbs. This paper investigates a novel class of overconstrained locomotion from a design and learning perspective inspired by evolutionary morphology, aiming to integrate the concept of `intelligent design under constraints' - hereafter referred to as constraint-driven design intelligence - in developing modern robotic limbs with superior energy efficiency. We propose a 3D-printable design of robotic limbs parametrically reconfigurable as a classical planar 4-bar linkage, an overconstrained Bennett linkage, and a spherical 4-bar linkage. These limbs adopt a co-axial actuation, identical to the modern legged robot platforms, with the added capability of upgrading into a wheel-legged system. Then, we implemented a large-scale, multi-terrain deep reinforcement learning framework to train these reconfigurable limbs for a comparative analysis of overconstrained locomotion in energy efficiency. Results show that the overconstrained limbs exhibit more efficient locomotion than planar limbs during forward and sideways walking over different terrains, including floors, slopes, and stairs, with or without random noises, by saving at least 22% mechanical energy in completing the traverse task, with the spherical limbs being the least efficient. It also achieves the highest average speed of 0.85 meters per second on flat terrain, which is 20% faster than the planar limbs. This study paves the path for an exciting direction for future research in overconstrained robotics leveraging evolutionary morphology and reconfigurable mechanism intelligence when combined with state-of-the-art methods in deep reinforcement learning.

cs.RO↗