arXiv subjects

Jin Cheng

Publications and source records attributed to Jin Cheng.

At least 37 records · Page 2Linked to original sources

arXiv2025

Learning More With Less: Sample Efficient Model-Based RL for Loco-Manipulation

By combining the agility of legged locomotion with the capabilities of manipulation, loco-manipulation platforms have the potential to perform complex tasks in real-world applications. To this end, state-of-the-art quadrupeds with manipulators, such as the Boston Dynamics Spot, have emerged to provide a capable and robust platform. However, the complexity of loco-manipulation control, as well as the black-box nature of commercial platforms, pose challenges for deriving accurate dynamics models and robust control policies. To address these challenges, we turn to model-based reinforcement learning (RL). We develop a hand-crafted kinematic model of a quadruped-with-arm platform which - employing recent advances in Bayesian Neural Network (BNN)-based learning - we use as a physical prior to efficiently learn an accurate dynamics model from limited data. We then leverage our learned model to derive control policies for loco-manipulation via RL. We demonstrate the effectiveness of our approach on state-of-the-art hardware using the Boston Dynamics Spot, accurately performing dynamic end-effector trajectory tracking even in low data regimes. Project website and videos: https://sites.google.com/view/learning-more-with-less.

cs.RO↗

arXiv2025

RAMBO: RL-Augmented Model-Based Whole-Body Control for Loco-Manipulation

Loco-manipulation, physical interaction of various objects that is concurrently coordinated with locomotion, remains a major challenge for legged robots due to the need for both precise end-effector control and robustness to unmodeled dynamics. While model-based controllers provide precise planning via online optimization, they are limited by model inaccuracies. In contrast, learning-based methods offer robustness, but they struggle with precise modulation of interaction forces. We introduce RAMBO, a hybrid framework that integrates model-based whole-body control within a feedback policy trained with reinforcement learning. The model-based module generates feedforward torques by solving a quadratic program, while the policy provides feedback corrective terms to enhance robustness. We validate our framework on a quadruped robot across a diverse set of real-world loco-manipulation tasks, such as pushing a shopping cart, balancing a plate, and holding soft objects, in both quadrupedal and bipedal walking. Our experiments demonstrate that RAMBO enables precise manipulation capabilities while achieving robust and dynamic locomotion.

cs.RO↗

arXiv2025

Spatio-Temporal Motion Retargeting for Quadruped Robots

This work presents a motion retargeting approach for legged robots, aimed at transferring the dynamic and agile movements to robots from source motions. In particular, we guide the imitation learning procedures by transferring motions from source to target, effectively bridging the morphological disparities while ensuring the physical feasibility of the target system. In the first stage, we focus on motion retargeting at the kinematic level by generating kinematically feasible whole-body motions from keypoint trajectories. Following this, we refine the motion at the dynamic level by adjusting it in the temporal domain while adhering to physical constraints. This process facilitates policy training via reinforcement learning, enabling precise and robust motion tracking. We demonstrate that our approach successfully transforms noisy motion sources, such as hand-held camera videos, into robot-specific motions that align with the morphology and physical properties of the target robots. Moreover, we demonstrate terrain-aware motion retargeting to perform BackFlip on top of a box. We successfully deployed these skills to four robots with different dimensions and physical properties in the real world through hardware experiments.

cs.RO↗

arXiv2025

Tensor product modules over the planar Galilean conformal algebra from free modules of rank one

In this paper, we investigate the irreducible tensor product modules over the planar Galilean conformal algebra $\mathcal{G}$ named by Aizawa, which is the infinite-dimensional Galilean conformal algebra introduced by Bagchi-Gopakumar in $(2+1)$ dimensional space-time. We give the necessary and sufficient conditions for the tensor product modules of any two of $\mathcal{U}(\mathfrak{h})$-free modules of rank one over $\mathcal{G}$ to be irreducible, where $\mathfrak{h}$ is the Cartan subalgebra of $\mathcal{G}$.Furthermore, the isomorphism classes of these irreducible tensor product modules are determined. As an application, we obtain the necessary conditions for the tensor product modules of any two of $\mathcal{U}(\mathbb{C} L_0)$-free modules of rank one over Witt algebra and Heisenberg-Virasoro algebra to be irreducible.

math.RT↗

arXiv2025

SATA: Safe and Adaptive Torque-Based Locomotion Policies Inspired by Animal Learning

Despite recent advances in learning-based controllers for legged robots, deployments in human-centric environments remain limited by safety concerns. Most of these approaches use position-based control, where policies output target joint angles that must be processed by a low-level controller (e.g., PD or impedance controllers) to compute joint torques. Although impressive results have been achieved in controlled real-world scenarios, these methods often struggle with compliance and adaptability when encountering environments or disturbances unseen during training, potentially resulting in extreme or unsafe behaviors. Inspired by how animals achieve smooth and adaptive movements by controlling muscle extension and contraction, torque-based policies offer a promising alternative by enabling precise and direct control of the actuators in torque space. In principle, this approach facilitates more effective interactions with the environment, resulting in safer and more adaptable behaviors. However, challenges such as a highly nonlinear state space and inefficient exploration during training have hindered their broader adoption. To address these limitations, we propose SATA, a bio-inspired framework that mimics key biomechanical principles and adaptive learning mechanisms observed in animal locomotion. Our approach effectively addresses the inherent challenges of learning torque-based policies by significantly improving early-stage exploration, leading to high-performance final policies. Remarkably, our method achieves zero-shot sim-to-real transfer. Our experimental results indicate that SATA demonstrates remarkable compliance and safety, even in challenging environments such as soft/slippery terrain or narrow passages, and under significant external disturbances, highlighting its potential for practical deployments in human-centric and safety-critical scenarios.

cs.RO↗

arXiv2024

RobotKeyframing: Learning Locomotion with High-Level Objectives via Mixture of Dense and Sparse Rewards

This paper presents a novel learning-based control framework that uses keyframing to incorporate high-level objectives in natural locomotion for legged robots. These high-level objectives are specified as a variable number of partial or complete pose targets that are spaced arbitrarily in time. Our proposed framework utilizes a multi-critic reinforcement learning algorithm to effectively handle the mixture of dense and sparse rewards. Additionally, it employs a transformer-based encoder to accommodate a variable number of input targets, each associated with specific time-to-arrivals. Throughout simulation and hardware experiments, we demonstrate that our framework can effectively satisfy the target keyframe sequence at the required times. In the experiments, the multi-critic method significantly reduces the effort of hyperparameter tuning compared to the standard single-critic alternative. Moreover, the proposed transformer-based architecture enables robots to anticipate future goals, which results in quantitative improvements in their ability to reach their targets.

cs.RO↗

arXiv2024

MetaLoco: Universal Quadrupedal Locomotion with Meta-Reinforcement Learning and Motion Imitation

This work presents a meta-reinforcement learning approach to develop a universal locomotion control policy capable of zero-shot generalization across diverse quadrupedal platforms. The proposed method trains an RL agent equipped with a memory unit to imitate reference motions using a small set of procedurally generated quadruped robots. Through comprehensive simulation and real-world hardware experiments, we demonstrate the efficacy of our approach in achieving locomotion across various robots without requiring robot-specific fine-tuning. Furthermore, we highlight the critical role of the memory unit in enabling generalization, facilitating rapid adaptation to changes in the robot properties, and improving sample efficiency.

cs.RO↗

arXiv2024

DARE: Diffusion Policy for Autonomous Robot Exploration

Autonomous robot exploration requires a robot to efficiently explore and map unknown environments. Compared to conventional methods that can only optimize paths based on the current robot belief, learning-based methods show the potential to achieve improved performance by drawing on past experiences to reason about unknown areas. In this paper, we propose DARE, a novel generative approach that leverages diffusion models trained on expert demonstrations, which can explicitly generate an exploration path through one-time inference. We build DARE upon an attention-based encoder and a diffusion policy model, and introduce ground truth optimal demonstrations for training to learn better patterns for exploration. The trained planner can reason about the partial belief to recognize the potential structure in unknown areas and consider these areas during path planning. Our experiments demonstrate that DARE achieves on-par performance with both conventional and learning-based state-of-the-art exploration planners, as well as good generalizability in both simulations and real-life scenarios.

cs.RO↗

arXiv2024

RL + Model-based Control: Using On-demand Optimal Control to Learn Versatile Legged Locomotion

This paper presents a control framework that combines model-based optimal control and reinforcement learning (RL) to achieve versatile and robust legged locomotion. Our approach enhances the RL training process by incorporating on-demand reference motions generated through finite-horizon optimal control, covering a broad range of velocities and gaits. These reference motions serve as targets for the RL policy to imitate, leading to the development of robust control policies that can be learned with reliability. Furthermore, by utilizing realistic simulation data that captures whole-body dynamics, RL effectively overcomes the inherent limitations in reference motions imposed by modeling simplifications. We validate the robustness and controllability of the RL training process within our framework through a series of experiments. In these experiments, our method showcases its capability to generalize reference motions and effectively handle more complex locomotion tasks that may pose challenges for the simplified model, thanks to RL's flexibility. Additionally, our framework effortlessly supports the training of control policies for robots with diverse dimensions, eliminating the necessity for robot-specific adjustments in the reward function and hyperparameters.

cs.RO↗

arXiv2024

Offline Diversity Maximization Under Imitation Constraints

There has been significant recent progress in the area of unsupervised skill discovery, utilizing various information-theoretic objectives as measures of diversity. Despite these advances, challenges remain: current methods require significant online interaction, fail to leverage vast amounts of available task-agnostic data and typically lack a quantitative measure of skill utility. We address these challenges by proposing a principled offline algorithm for unsupervised skill discovery that, in addition to maximizing diversity, ensures that each learned skill imitates state-only expert demonstrations to a certain degree. Our main analytical contribution is to connect Fenchel duality, reinforcement learning, and unsupervised skill discovery to maximize a mutual information objective subject to KL-divergence state occupancy constraints. Furthermore, we demonstrate the effectiveness of our method on the standard offline benchmark D4RL and on a custom offline dataset collected from a 12-DoF quadruped robot for which the policies trained in simulation transfer well to the real robotic system.

cs.LG↗

arXiv2024

Hadamard integrators for wave equations in time and frequency domain: Eulerian formulations via butterfly algorithms

Starting from the Kirchhoff-Huygens representation and Duhamel's principle of time-domain wave equations, we propose novel butterfly-compressed Hadamard integrators for self-adjoint wave equations in both time and frequency domain in an inhomogeneous medium. First, we incorporate the leading term of Hadamard's ansatz into the Kirchhoff-Huygens representation to develop a short-time valid propagator. Second, using the Fourier transform in time, we derive the corresponding Eulerian short-time propagator in frequency domain; on top of this propagator, we further develop a time-frequency-time (TFT) method for the Cauchy problem of time-domain wave equations. Third, we further propose the time-frequency-time-frequency (TFTF) method for the corresponding point-source Helmholtz equation, which provides Green's functions of the Helmholtz equation for all angular frequencies within a given frequency band. Fourth, to implement TFT and TFTF methods efficiently, we introduce butterfly algorithms to compress oscillatory integral kernels at different frequencies. As a result, the proposed methods can construct wave field beyond caustics implicitly and advance spatially overturning waves in time naturally with quasi-optimal computational complexity and memory usage. Furthermore, once constructed the Hadamard integrators can be employed to solve both time-domain wave equations with various initial conditions and frequency-domain wave equations with different point sources. Numerical examples for two-dimensional wave equations illustrate the accuracy and efficiency of the proposed methods.

math.NA↗

arXiv2024

Quantitative Analysis of Molecular Transport in the Extracellular Space Using Physics-Informed Neural Network

The brain extracellular space (ECS), an irregular, extremely tortuous nanoscale space located between cells or between cells and blood vessels, is crucial for nerve cell survival. It plays a pivotal role in high-level brain functions such as memory, emotion, and sensation. However, the specific form of molecular transport within the ECS remain elusive. To address this challenge, this paper proposes a novel approach to quantitatively analyze the molecular transport within the ECS by solving an inverse problem derived from the advection-diffusion equation (ADE) using a physics-informed neural network (PINN). PINN provides a streamlined solution to the ADE without the need for intricate mathematical formulations or grid settings. Additionally, the optimization of PINN facilitates the automatic computation of the diffusion coefficient governing long-term molecule transport and the velocity of molecules driven by advection. Consequently, the proposed method allows for the quantitative analysis and identification of the specific pattern of molecular transport within the ECS through the calculation of the Peclet number. Experimental validation on two datasets of magnetic resonance images (MRIs) captured at different time points showcases the effectiveness of the proposed method. Notably, our simulations reveal identical molecular transport patterns between datasets representing rats with tracer injected into the same brain region. These findings highlight the potential of PINN as a promising tool for comprehensively exploring molecular transport within the ECS.

cs.AI↗

arXiv2024

Learning based numerical methods for Helmholtz equation with high frequency

High-frequency issues have been remarkably challenges in numerical methods for partial differential equations. In this paper, a learning based numerical method (LbNM) is proposed for Helmholtz equation with high frequency. The main novelty is using Tikhonov regularization method to stably learn the solution operator by utilizing relevant information especially the fundamental solutions. Then applying the solution operator to a new boundary input could quickly update the solution. Based on the method of fundamental solutions and the quantitative Runge approximation, we give the error estimate. This indicates interpretability and generalizability of the present method. Numerical results validates the error analysis and demonstrates the high-precision and high-efficiency features.

math.NA↗

arXiv2023

Learning Diverse Skills for Local Navigation under Multi-constraint Optimality

Despite many successful applications of data-driven control in robotics, extracting meaningful diverse behaviors remains a challenge. Typically, task performance needs to be compromised in order to achieve diversity. In many scenarios, task requirements are specified as a multitude of reward terms, each requiring a different trade-off. In this work, we take a constrained optimization viewpoint on the quality-diversity trade-off and show that we can obtain diverse policies while imposing constraints on their value functions which are defined through distinct rewards. In line with previous work, further control of the diversity level can be achieved through an attract-repel reward term motivated by the Van der Waals force. We demonstrate the effectiveness of our method on a local navigation task where a quadruped robot needs to reach the target within a finite horizon. Finally, our trained policies transfer well to the real 12-DoF quadruped robot, Solo12, and exhibit diverse agile behaviors with successful obstacle traversal.

cs.RO↗

arXiv2023

Hadamard integrator for time-dependent wave equations: Lagrangian formulation via ray tracing

We propose a novel Hadamard integrator for the self-adjoint time-dependent wave equation in an inhomogeneous medium. First, we create a new asymptotic series based on the Gelfand-Shilov function, dubbed Hadamard's ansatz, to approximate the Green's function of the time-dependent wave equation. Second, incorporating the leading term of Hadamard's ansatz into the Kirchhoff-Huygens representation, we develop an original Hadamard integrator for the Cauchy problem of the time-dependent wave equation and derive the corresponding Lagrangian formulation in geodesic polar coordinates. Third, to construct the Hadamard integrator in the Lagrangian formulation efficiently, we use a short-time ray tracing method to obtain wavefront locations accurately, and we further develop fast algorithms to compute Chebyshev-polynomial based low-rank representations of both wavefront locations and variants of Hadamard coefficients. Fourth, equipped with these low-rank representations, we apply the Hadamard integrator to efficiently solve time-dependent wave equations with highly oscillatory initial conditions, where the time step size is independent of the initial conditions. By judiciously choosing the medium-dependent time step, our new Hadamard integrator can propagate wave field beyond caustics implicitly and advance spatially overturning waves in time naturally. Moreover, since the integrator is independent of initial conditions, the Hadamard integrator can be applied to many different initial conditions once it is constructed. Both two-dimensional and three-dimensional numerical examples illustrate the accuracy and performance of the proposed method.

math.NA↗

arXiv2023

Harmonic Measures and Numerical Computation of Cauchy Problems for Laplace Equations

It is well known that Cauchy problem for Laplace equations is an ill-posed problem in Hadamard's sense. Small deviations in Cauchy data may lead to large errors in the solutions. It is observed that if a bound is imposed on the solution, there exists a conditional stability estimate. This gives a reasonable way to construct stable algorithms. However, it is impossible to have good results at all points in the domain. Although numerical methods for Cauchy problems for Laplace equations have been widely studied for quite a long time, there are still some unclear points, for example, how to evaluate the numerical solutions, which means whether we can approximate the Cauchy data well and keep the bound of the solution, and at which points the numerical results are reliable? In this paper, we will prove the conditional stability estimate which is quantitatively related to harmonic measures. The harmonic measure can be used as an indicate function to pointwisely evaluate the numerical result, which further enables us to find a reliable subdomain where the local convergence rate is higher than a certain order.

math.NA↗

arXiv2022

Haptic Teleoperation of High-dimensional Robotic Systems Using a Feedback MPC Framework

Model Predictive Control (MPC) schemes have proven their efficiency in controlling high degree-of-freedom (DoF) complex robotic systems. However, they come at a high computational cost and an update rate of about tens of hertz. This relatively slow update rate hinders the possibility of stable haptic teleoperation of such systems since the slow feedback loops can cause instabilities and loss of transparency to the operator. This work presents a novel framework for transparent teleoperation of MPC-controlled complex robotic systems. In particular, we employ a feedback MPC approach and exploit its structure to account for the operator input at a fast rate which is independent of the update rate of the MPC loop itself. We demonstrate our framework on a mobile manipulator platform and show that it significantly improves haptic teleoperation's transparency and stability. We also highlight that the proposed feedback structure is constraint satisfactory and does not violate any constraints defined in the optimal control problem. To the best of our knowledge, this work is the first realization of the bilateral teleoperation of a legged manipulator using a whole-body MPC framework.

cs.RO↗

arXiv2021

Determination of source terms in diffusion and wave equations by observations after incidents: uniqueness and stability

We consider a diffusion and a wave equations: $$ \partial_t^ku(x,t) = Δu(x,t) + μ(t)f(x), \quad x\in Ω, \, t>0, \quad k=1,2 $$ with the zero initial and boundary conditions, where $Ω\subset \mathbb{R}^d$ is a bounded domain. We establish uniqueness and/or stability results for inverse problems of 1. determining $μ(t)$, $0<t<T$ with given $f(x)$; 2. determining $f(x)$, $x\in Ω$ with given $μ(t)$ \end{itemize} by data of $u$: $u(x_0,\cdot)$ with fixed point $x_0\in Ω$ or Neumann data on subboundary over time interval. In our inverse problems, data are taken over time interval $T_1<t<T_1$, by assuming that $T<T_1<T_2$ and $μ(t)=0$ for $t\ge T$, which means that the source stops to be active after the time $T$ and the observations are started only after $T$. This assumption is practical by such a posteriori data after incidents, although inverse problems had been well studied in the case of $T=0$. We establish the non-uniqueness, the uniqueness and conditional stability for a diffusion and a wave equations. The proofs are based on eigenfunction expansions of the solutions $u(x,t)$, and we rely on various knowledge of the generalized Weierstrass theorem on polynomial approximation, almost periodic functions, Carleman estimate, non-harmonic Fourier series.

math.AP↗