A Framework for Deploying Learning-based Quadruped Loco-Manipulation

• URL: http://arxiv.org/abs/2512.18938v1
• Date: Mon, 22 Dec 2025 01:19:26 GMT
• Title: A Framework for Deploying Learning-based Quadruped Loco-Manipulation
• Abstract summary: We present an open pipeline for training, benchmarking, and deploying RL-based controllers on the Unitree B1 quadruped with a Z1 arm.<n>The framework unifies sim-to-sim and sim-to-real transfer through ROS, re-implementing a policy trained in Isaac Gym, extending it to MuJoCo via a hardware abstraction layer, and deploying the same controller on physical hardware.
• Score: 9.16082538503878
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quadruped mobile manipulators offer strong potential for agile loco-manipulation but remain difficult to control and transfer reliably from simulation to reality. Reinforcement learning (RL) shows promise for whole-body control, yet most frameworks are proprietary and hard to reproduce on real hardware. We present an open pipeline for training, benchmarking, and deploying RL-based controllers on the Unitree B1 quadruped with a Z1 arm. The framework unifies sim-to-sim and sim-to-real transfer through ROS, re-implementing a policy trained in Isaac Gym, extending it to MuJoCo via a hardware abstraction layer, and deploying the same controller on physical hardware. Sim-to-sim experiments expose discrepancies between Isaac Gym and MuJoCo contact models that influence policy behavior, while real-world teleoperated object-picking trials show that coordinated whole-body control extends reach and improves manipulation over floating-base baselines. The pipeline provides a transparent, reproducible foundation for developing and analyzing RL-based loco-manipulation controllers and will be released open source to support future research.

Related papers

• Isaac Sim-to-Real: Reinforcement Learning based Locomotion for Quadrupeds [0.3867363075280543]
  This work presents a robust RL locomotion framework capable of whole-body control.<n>The proposed framework utilizes Nvidia's new set of simulation tools, Isaac Sim, and its companion RL framework, Isaac Lab, for training, achieving a zero-shot sim-to-real policy.<n>The performance of our policy is validated on physical hardware using the Unitree Go1, with experimental results showing similar velocity tracking performance to the quadruped's integrated controller.
  arXiv  Detail & Related papers  (2026-07-20T16:27:56Z)
• Sim2Real-AD: A Modular Sim-to-Real Framework for Deploying VLM-Guided Reinforcement Learning in Real-World Autonomous Driving [13.424737198969247]
  This paper presents Sim2Real-AD, a modular framework for zero-shot sim-to-real transfer of VLM-guided RL policies to full-scale vehicles.<n>To the best of our knowledge, this study is among the first to demonstrate zero-shot closed-loop deployment of a CARLA-trained VLM-guided RL policy on a full-scale real vehicle.
  arXiv  Detail & Related papers  (2026-04-03T22:41:45Z)
• Simulating Environments with Reasoning Models for Agent Training [55.98861707136674]
  Building bespoke environments for training is heavy, brittle, and limits progress.<n>We propose two frameworks: Simia-SFT and Simia-RL.<n>Simia-SFT and Simia-RL enable scalable agent training without environment engineering.
  arXiv  Detail & Related papers  (2025-11-03T18:29:57Z)
• EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering [55.56674028743782]
  Large language model (LLM) steering has emerged as a promising paradigm for controlling model behavior at inference time.<n>We present EasySteer, a unified framework for high-performance, LLM steering built on vLLM.
  arXiv  Detail & Related papers  (2025-09-29T17:59:07Z)
• AI/ML Life Cycle Management for Interoperable AI Native RAN [50.61227317567369]
  Artificial intelligence (AI) and machine learning (ML) models are rapidly permeating the 5G Radio Access Network (RAN)<n>These developments lay the foundation for AI-native transceivers as a key enabler for 6G.
  arXiv  Detail & Related papers  (2025-07-24T16:04:59Z)
• TeleOpBench: A Simulator-Centric Benchmark for Dual-Arm Dexterous Teleoperation [50.261933845325636]
  We introduce TeleOpBench, a simulator-centric benchmark tailored to bimanual dexterous teleoperation.<n>Within this benchmark we implement four representative teleoperation modalities-(i) MoCap, (ii) VR device, (iii) arm-hand exoskeletons, and (iv) monocular vision tracking.
  arXiv  Detail & Related papers  (2025-05-19T06:08:53Z)
• Learning to Fly in Seconds [7.259696592534715]
  We show how curriculum learning and a highly optimized simulator enhance sample complexity and lead to fast training times. Our framework enables Simulation-to-Reality (Sim2Real) transfer for direct control after only 18 seconds of training on a consumer-grade laptop.
  arXiv  Detail & Related papers  (2023-11-22T01:06:45Z)
• Resilient Control of Networked Microgrids using Vertical Federated Reinforcement Learning: Designs and Real-Time Test-Bed Validations [5.394255369988441]
  This paper presents a novel federated reinforcement learning (Fed-RL) approach to tackle (a) model complexities, unknown dynamical behaviors of IBR devices, (b) privacy issues regarding data sharing in multi-party-owned networked grids, and (2) transfers learned controls from simulation to hardware-in-the-loop test-bed. Experiments show that the simulator-trained RL controllers produce convincing results with the real-time test-bed set-up, validating the minimization of sim-to-real gap.
  arXiv  Detail & Related papers  (2023-11-21T00:59:27Z)
• DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality [64.51295032956118]
  We train a policy that can perform robust dexterous manipulation on an anthropomorphic robot hand. Our work reaffirms the possibilities of sim-to-real transfer for dexterous manipulation in diverse kinds of hardware and simulator setups.
  arXiv  Detail & Related papers  (2022-10-25T01:51:36Z)
• Zero-Shot Uncertainty-Aware Deployment of Simulation Trained Policies on Real-World Robots [17.710172337571617]
  Deep reinforcement learning (RL) agents tend to make errors when deployed in the real world due to mismatches between the training and execution environments. We propose a novel uncertainty-aware deployment strategy that combines the strengths of deep RL policies and traditional handcrafted controllers. We show promising results on two real-world continuous control tasks, where BCF outperforms both the standalone policy and controller.
  arXiv  Detail & Related papers  (2021-12-10T02:13:01Z)
• Bayesian Controller Fusion: Leveraging Control Priors in Deep Reinforcement Learning for Robotics [17.660913275007317]
  We present a hybrid control strategy that combines the strengths of traditional hand-crafted controllers and model-free deep reinforcement learning (RL) BCF thrives in the robotics domain, where reliable but suboptimal control priors exist for many tasks, but RL from scratch remains unsafe and data-inefficient. We show BCF's applicability to the zero-shot sim-to-real setting and its ability to deal with out-of-distribution states in the real world.
  arXiv  Detail & Related papers  (2021-07-21T00:43:32Z)
• Residual Reinforcement Learning from Demonstrations [51.56457466788513]
  Residual reinforcement learning (RL) has been proposed as a way to solve challenging robotic tasks by adapting control actions from a conventional feedback controller to maximize a reward signal. We extend the residual formulation to learn from visual inputs and sparse rewards using demonstrations. Our experimental evaluation on simulated manipulation tasks on a 6-DoF UR5 arm and a 28-DoF dexterous hand demonstrates that residual RL from demonstrations is able to generalize to unseen environment conditions more flexibly than either behavioral cloning or RL fine-tuning.
  arXiv  Detail & Related papers  (2021-06-15T11:16:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.