ANYbotics Research

Research

  • 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
  • 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. ANYmal is the evaluation platform used to test the method… - 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. ANYmal is the robot platform used in the reported… - 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
  • Adaptive energy-regularization paper trains efficient gait transitions on ANYmal-C - 2024-03-29 - Research Publication - The paper proposes an adaptive energy reward for reinforcement-learning locomotion so quadrupeds can choose efficient gaits across different speeds. The authors demonstrate autonomous gait transitions on ANYmal-C and… - source: arxiv.org
  • ANYmal Parkour paper trains agile navigation for quadrupedal robots - 2023-06-26 - Research Publication - The ANYmal Parkour paper proposes a learned hierarchy for walking, jumping, climbing, and crouching through parkour-like obstacles. The authors report successful real-world transfer on hardware at speeds up to two meters… - source: arxiv.org
  • Perceptive locomotion paper validates real-time NMPC climbing on ANYmal - 2022-08-17 - Research Publication - The paper presents a full perception, planning, and control pipeline for optimizing all robot degrees of freedom in real time. Experiments on ANYmal cover gaps, slopes, and stepping stones, including dynamic climbing… - source: arxiv.org
  • ANYmal challenging-terrain paper demonstrates blind locomotion in natural environments - 2020-10-21 - Research Publication - The Science Robotics paper trains a learning-based controller for quadrupedal locomotion over difficult natural terrain. The controller is deployed on two generations of ANYmal robots in outdoor settings beyond the reach… - source: arxiv.org
  • Science Robotics paper learns agile motor skills on ANYmal - 2019-01-24 - Research Publication - The paper trains a neural-network locomotion controller in simulation and deploys it on the ANYmal quadruped. It reports dynamic motor skills such as fast locomotion, fall recovery, and robustness to pushes, slopes, and… - source: arxiv.org

Articles

View ANYbotics overview