ANYbotics connects ANYmal to industrial field-service workflows - 2026-03-30 - Article - ANYbotics and SAP are integrating ANYmal with SAP Field Service Management, giving industrial customers a way to route inspection work to robots and bring results back into maintenance, asset, and service workflows.
Learning Perceptive Platform Adaptive Locomotion Controllers for Quadrupedal Robots - 2026-06-23 - Research Publication - Universal quadrupedal locomotion remains limited by the difficulty of integrating perception across diverse robot morphologies. Policies are evaluated in simulation on flat and rough terrains, and deployed on ANYmal… - source: arxiv.org
Sensor Configuration Matters: A Systematic Evaluation of Multimodal SLAM on Quadruped Robots - 2026-06-17 - Research Publication - Quadrupeds introduce distinct embodiment-induced sensory challenges, including foot-impact shocks, high-frequency mechanical vibrations, and rapid angular rotations, which degrade standard perception pipelines. To address… - source: arxiv.org
ZackOo23/Software-Development-for-Advanced-RL-techniques - 2026-06-01 - Research Publication - This repository extends an ANYmal-D PPO baseline into a more maintainable robotics learning pipeline for advanced simulation. ANYmal-D Learning Pipeline Reproducible ANYmal-D robotics learning pipeline with PPO baseline… - source: github.com
SafeMind: A Risk-Aware Differentiable Control Framework for Adaptive and Safe Quadruped Locomotion - 2026-04-10 - Research Publication - The authors introduce SafeMind, a differentiable stochastic safety-control framework that unifies probabilistic Control Barrier Functions with semantic context understanding and meta-adaptive risk calibration. SafeMind is… - source: arxiv.org
GrandTour dataset paper releases large-scale ANYmal-D legged-robot perception data - 2026-02-20 - Research Publication - The GrandTour paper introduces a large open-access legged-robotics dataset for state estimation, SLAM, perception, and multi-modal learning. The dataset was collected with an ANYbotics ANYmal-D quadruped carrying the Boxi… - source: arxiv.org
Scaling Rough Terrain Locomotion with Automatic Curriculum Reinforcement Learning - 2026-01-24 - Research Publication - The authors propose a Learning Progress-based Automatic Curriculum Reinforcement Learning (LP-ACRL) framework, which estimates the agent's learning progress online and adaptively adjusts the task-sampling distribution… - source: arxiv.org
Large-Scale Autonomous Gas Monitoring for Volcanic Environments: A Legged Robot on Mount Etna - 2026-01-12 - Research Publication - The authors present a legged robotic system for autonomous volcanic gas analysis, utilizing the quadruped ANYmal, equipped with a quadrupole mass spectrometer system. The authors evaluated the system on Mount Etna across… - source: arxiv.org
Botany Meets Robotics in Alpine Scree Monitoring - 2025-11-16 - Research Publication - The paper presents a novel approach for scree habitat monitoring using a legged robot to assist botanists in data collection and species identification. This paper presents a novel approach for scree habitat monitoring… - source: arxiv.org
PGTT: Phase-Guided Terrain Traversal for Perceptive Legged Locomotion - 2025-10-21 - Research Publication - The authors propose Phase-Guided Terrain Traversal (PGTT), a perception-aware deep-RL approach that overcomes these limitations by enforcing gait structure purely through reward shaping, thereby reducing inductive bias in… - source: arxiv.org
Bridging Research and Practice in Simulation-based Testing of Industrial Robot Navigation Systems - 2025-10-10 - Research Publication - The paper presents the industrial adoption of Surrealist, a simulation-based test generation framework originally for UAVs, now applied to the ANYmal quadrupedal robot for industrial inspection. In a pilot phase, generated… - source: arxiv.org
Sampling Strategies for Robust Universal Quadrupedal Locomotion Policies - 2025-10-08 - Research Publication - This work focuses on sampling strategies of configuration variations for generating robust universal locomotion policies for quadrupedal robots. All training was conducted using the RaiSim simulation environment, tested in… - source: arxiv.org
Collaborative Loco-Manipulation for Pick-and-Place Tasks with Dynamic Reward Curriculum - 2025-09-16 - Research Publication - The authors present a hierarchical RL pipeline for training one-armed legged robots to perform pick-and-place (P&P) tasks end-to-end -- from approaching the payload to releasing it at a target area -- in both single-robot… - source: arxiv.org
Towards bridging the gap: Systematic sim-to-real transfer for diverse legged robots - 2025-09-08 - Research Publication - The authors propose a framework that integrates sim-to-real reinforcement learning with a physics-grounded energy model for permanent magnet synchronous motors. All code, models, and datasets will be released. - source: arxiv.org
Constrained Style Learning from Imperfect Demonstrations under Task Optimality - 2025-07-12 - Research Publication - The authors introduce an adaptively adjustable Lagrangian multiplier to guide the agent to imitate demonstrations selectively, capturing stylistic nuances without compromising task performance. The authors validate the… - source: arxiv.org
Building Forest Inventories with Autonomous Legged Robots -- System, Lessons, and Challenges Ahead - 2025-06-25 - Research Publication - The paper presents a prototype system for autonomous, under-canopy forest inventory with legged platforms. The authors report the performance of the system from trials executed over one and a half years in forests in three… - source: arxiv.org
Learning Physical Systems: Symplectification via Gauge Fixing in Dirac Structures - 2025-06-23 - Research Publication - The authors tackle this foundational limitation by introducing Presymplectification Networks (PSNs), the first framework to learn the symplectification lift via Dirac structures, restoring a non-degenerate symplectic… - source: arxiv.org
Parkour in the Wild: Learning a General and Extensible Agile Locomotion Policy Using Multi-expert Distillation and RL Fine-tuning - 2025-05-16 - Research Publication - Legged robots are well-suited for navigating terrains inaccessible to wheeled robots, making them ideal for applications in search and rescue or space exploration. The work is explicitly tied to ANYmal, making the product… - source: arxiv.org
Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoning - 2025-05-15 - Research Publication - While foundation models offer promise toward improving robot safety in out-of-distribution (OOD) scenarios, how to effectively harness their generalist knowledge for real-time, dynamically feasible response remains a… - source: arxiv.org
FOCI: Trajectory Optimization on Gaussian Splats - 2025-05-13 - Research Publication - 3D Gaussian Splatting (3DGS) has recently gained popularity as a faster alternative to Neural Radiance Fields (NeRFs) in 3D reconstruction and view synthesis methods. The work is explicitly tied to ANYmal, making the… - source: arxiv.org
Offline Adaptation of Quadruped Locomotion using Diffusion Models - 2024-11-13 - Research Publication - The authors present a diffusion-based approach to quadrupedal locomotion that simultaneously addresses the limitations of learning and interpolating between multiple skills and of (modes) offline adapting to new locomotion… - source: arxiv.org
SDS -- See it, Do it, Sorted: Quadruped Skill Synthesis from Single Video Demonstration - 2024-10-15 - Research Publication - ANYmal) and outperforms prior work in data efficiency, training time and engineering effort. Further materials and the code are open-source under: https://rpl-cs-ucl.github.io/SDSweb/. - source: arxiv.org
Constrained skill discovery paper deploys unsupervised locomotion on ANYmal - 2024-10-10 - Research Publication - The paper proposes constrained unsupervised skill discovery for quadruped locomotion using a latent representation over states. The authors report deployment of learned policies on a real ANYmal quadruped robot for… - source: arxiv.org
Obstacle-Avoidant Leader Following with a Quadruped Robot - 2024-10-01 - Research Publication - This work presents a virtual leash with which a robot can naturally follow an operator. The authors successfully validate on the ANYmal platform the robustness and performance of their entire pipeline in real-world… - source: arxiv.org