We propose a learning-based method to reconstruct the local terrain for locomotion with a mobile robot traversing urban environments. Using a stream of depth measurements from the onboard cameras and the robot's trajectory, the algorithm estimates the topography in the robot's vicinity. The raw measurements from these cameras are noisy and only provide partial and occluded observations that in many cases do not show the terrain the robot stands on. Therefore, we propose a 3D reconstruction model that faithfully reconstructs the scene, despite the noisy measurements and large amounts of missing data coming from the blind spots of the camera arrangement. The model consists of a 4D fully convolutional network on point clouds that learns the geometric priors to complete the scene from the context and an auto-regressive feedback to leverage spatio-temporal consistency and use evidence from the past. The network can be solely trained with synthetic data, and due to extensive augmentation, it is robust in the real world, as shown in the validation on a quadrupedal robot, ANYmal, traversing challenging settings. We run the pipeline on the robot's onboard low-power computer using an efficient sparse tensor implementation and show that the proposed method outperforms classical map representations.
Legged robots need to be capable of walking on diverse terrain conditions. In this paper, we present a novel reinforcement learning framework for learning locomotion on non-rigid dynamic terrains. Specifically, our framework can generate quadruped locomotion on flat elastic terrain that consists of a matrix of tiles moving up and down passively when pushed by the robot's feet. A trained robot with 55cm base length can walk on terrain that can sink up to 5cm. We propose a set of observation and reward terms that enable this locomotion; in which we found that it is crucial to include the end-eff…
GenTe: Generative Real-world Terrains for General Legged Robot Locomotion Control
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）理工学院）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）
Animals are capable of precise and agile locomotion using vision. Replicating this ability has been a long-standing goal in robotics. The traditional approach has been to decompose this problem into elevation mapping and foothold planning phases. The elevation mapping, however, is susceptible to failure and large noise artifacts, requires specialized hardware, and is biologically implausible. In this paper, we present the first end-to-end locomotion system capable of traversing stairs, curbs, stepping stones, and gaps. We show this result on a medium-sized quadruped robot using a single front-…
BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds
Shanghai AI Laboratory（上海人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）；Zhejiang University（浙江大学）；The University of Hong Kong（香港大学）；The Chinese University of Hong Kong（香港中文大学）
Legged locomotion is commonly studied and expressed as a discrete set of gait patterns, like walk, trot, gallop, which are usually treated as given and pre-programmed in legged robots for efficient locomotion at different speeds. However, fixing a set of pre-programmed gaits limits the generality of locomotion. Recent animal motor studies show that these conventional gaits are only prevalent in ideal flat terrain conditions while real-world locomotion is unstructured and more like bouts of intermittent steps. What principles could lead to both structured and unstructured patterns across mammal…
This paper presents a deep learning framework that is capable of solving partially observable locomotion tasks based on our novel interpretation of Recurrent Deterministic Policy Gradient (RDPG). We study on bias of sampled error measure and its variance induced by the partial observability of environment and subtrajectory sampling, respectively. Three major improvements are introduced in our RDPG based learning framework: tail-step bootstrap of interpolated temporal difference, initialisation of hidden state using past trajectory scanning, and injection of external experiences learned by othe…
Robert Bosch Centre for Cyber Physical Systems（罗伯特·博世网络物理系统中心）；Indian Institute of Science（印度科学学院）
In this paper, with a view toward fast deployment of locomotion gaits in low-cost hardware, we use a linear policy for realizing end-foot trajectories in the quadruped robot, Stoch $2$. In particular, the parameters of the end-foot trajectories are shaped via a linear feedback policy that takes the torso orientation and the terrain slope as inputs. The corresponding desired joint angles are obtained via an inverse kinematics solver and tracked via a PID control law. Augmented Random Search, a model-free and a gradient-free learning algorithm is used to train this linear policy. Simulation resu…
Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS)（深圳市人工智能与机器人研究院）；Institute of Robotics and Intelligent Manufacturing (IRIM), The Chinese University of Hong Kong (CUHK)（香港中文大学机器人与智能制造研究院）；George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology（佐治亚理工学院乔治·W·伍德拉夫机械工程学院）；Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院）
Dynamic quadrupedal locomotion over rough terrains reveals remarkable progress over the last few decades. Small-scale quadruped robots are adequately flexible and adaptable to traverse uneven terrains along sagittal direction, such as slopes and stairs. To accomplish autonomous locomotion navigation in complex environments, spinning is a fundamental yet indispensable functionality for legged robots. However, spinning behaviors of quadruped robots on uneven terrain often exhibit position drifts. Motivated by this problem, this study presents an algorithmic method to enable accurate spinning mot…
Google Brain Robotics（谷歌大脑机器人）；Georgia Institute of Technology（佐治亚理工学院）
Legged robots have unparalleled mobility on unstructured terrains. However, it remains an open challenge to design locomotion controllers that can operate in a large variety of environments. In this paper, we address this challenge of automatically learning locomotion controllers that can generalize to a diverse collection of terrains often encountered in the real world. We frame this challenge as a multi-task reinforcement learning problem and define each task as a type of terrain that the robot needs to traverse. We propose an end-to-end learning approach that makes direct use of the raw ext…
Istituto Italiano di Tecnologia（意大利技术研究院）；Università degli Studi di Genova（热那亚大学）；Swiss Federal Institute of Technology at Lausanne（洛桑联邦理工学院）；University of Texas（德克萨斯大学）；University of Naples Federico II（那不勒斯费德里科二世大学）
(Simplified Abstract) To accomplish breakthroughs in dynamic whole-body locomotion, legged robots have to be terrain aware. Terrain-Aware Locomotion (TAL) implies that the robot can perceive the terrain with its sensors, and can take decisions based on this information. This thesis presents TAL strategies both from a proprioceptive and an exteroceptive perspective. The strategies are implemented at the level of locomotion planning, control, and state estimation, and using optimization and learning techniques. The first part is on TAL strategies at the Whole-Body Control (WBC) level. We introdu…
Teacher Motion Priors: Enhancing Robot Locomotion over Challenging Terrain
University of Chinese Academy of Sciences（中国科学院大学）；Chinese Academy of Sciences（中国科学院）；Beijing Zhongke Huiling Robot Technology Co., LTD（北京中科创联机器人技术有限公司）
National University of Defense Technology（国防科技大学）；College of Intelligence Science and Technology（智能科学与技术学院）；Robotics Research Center（机器人研究中心）
In this paper, we propose a robust controller that achieves natural and stably fast locomotion on a real blind quadruped robot. With only proprioceptive information, the quadruped robot can move at a maximum speed of 10 times its body length, and has the ability to pass through various complex terrains. The controller is trained in the simulation environment by model-free reinforcement learning. In this paper, the proposed loose neighborhood control architecture not only guarantees the learning rate, but also obtains an action network that is easy to transfer to a real quadruped robot. Our res…
Optimizing gait stability for legged robots is a difficult problem. Even on level surfaces, effectively traversing across different textures (e.g., carpet) rests on dynamically tuning parameters in multidimensional space. Inspired by biology, evolutionary algorithms (EA) remain an attractive solution for feasibly implementing robotic locomotion with both energetic economy and rapid parameter convergence. Here, we leveraged this class of algorithms to evolve a stable hexapod gait controller capable of traversing uneven terrain and obstacles. Gait parameters were evolved in a rigid body dynamics…
Legged robots are becoming increasingly powerful and popular in recent years for their potential to bring the mobility of autonomous agents to the next level. This work presents a deep reinforcement learning approach that learns a robust Lidar-based perceptual locomotion policy in a partially observable environment using Proximal Policy Optimisation. Visual perception is critical to actively overcome challenging terrains, and to do so, we propose a novel learning strategy: Dynamic Reward Strategy (DRS), which serves as effective heuristics to learn a versatile gait using a neural network archi…
Teaching robots to learn diverse locomotion skills under complex three-dimensional environmental settings via Reinforcement Learning (RL) is still challenging. It has been shown that training agents in simple settings before moving them on to complex settings improves the training process, but so far only in the context of relatively simple locomotion skills. In this work, we adapt the Enhanced Paired Open-Ended Trailblazer (ePOET) approach to train more complex agents to walk efficiently on complex three-dimensional terrains. First, to generate more rugged and diverse three-dimensional traini…
Trajectory-Level Automatic Curriculum Learning for Legged Locomotion on Unstructured Terrain
National Key Laboratory of General Artificial Intelligence, BIGAI（通用人工智能国家重点实验室（BIGAI））；Beijing Normal University（北京师范大学）；Communication University of China（中国传媒大学）；Shanghai Jiao Tong University（上海交通大学）
Terrain-Aware Quadrupedal Locomotion via Reinforcement Learning
Tencent Robotics X（腾讯Robotics X）；The Chinese University of Hong Kong（香港中文大学）；Southern University of Science and Technology（南方科技大学）；University of Alberta（阿尔伯塔大学）
This work is on vision-based planning strategies for legged robots that separate locomotion planning into foothold selection and pose adaptation. Current pose adaptation strategies optimize the robot's body pose relative to given footholds. If these footholds are not reached, the robot may end up in a state with no reachable safe footholds. Therefore, we present a Vision-Based Terrain-Aware Locomotion (ViTAL) strategy that consists of novel pose adaptation and foothold selection algorithms. ViTAL introduces a different paradigm in pose adaptation that does not optimize the body pose relative t…
Look Forward to Walk Backward: Efficient Terrain Memory for Backward Locomotion with Forward Vision
Institute of Cyber-Systems and Control, Zhejiang University（浙江大学控制系统研究所）；College of Artificial Intelligence, Nankai University（南开大学人工智能学院）；Hangzhou Public Library（杭州公共图书馆）
Indian Institute of Technology (BHU) Varanasi（印度理工学院（巴纳拉斯印度教大学）瓦拉纳西分校）；Indian Institute of Technology Roorkee（印度理工学院鲁尔基分校）；Ohio State University（俄亥俄州立大学）；Indian Institute of Science（印度科学学院）
In this paper, with a view toward deployment of light-weight control frameworks for bipedal walking robots, we realize end-foot trajectories that are shaped by a single linear feedback policy. We learn this policy via a model-free and a gradient-free learning algorithm, Augmented Random Search (ARS), in the two robot platforms Rabbit and Digit. Our contributions are two-fold: a) By using torso and support plane orientation as inputs, we achieve robust walking on slopes of up to 20 degrees in simulation. b) We demonstrate additional behaviors like walking backwards, stepping-in-place, and recov…
Evolutionary Morphology Towards Overconstrained Locomotion via Large-Scale, Multi-Terrain Deep Reinforcement Learning
Southern University of Science and Technology（南方科技大学）；School of Design（设计学院）；Department of Mechanical and Energy Engineering（机械与能源工程系）；Department of System Design and Intelligent Manufacturing（系统设计与智能制造系）
Istituto Italiano di Tecnologia（意大利理工学院）；University of Oxford（牛津大学）；LAAS-CNRS（法国国家科学研究中心自动化系统实验室）
The quality of the visual feedback can vary significantly on a legged robot that is meant to traverse unknown and unstructured terrains. The map of the environment, acquired with online state-of-the-art algorithms, often degrades after a few steps, due to sensing inaccuracies, slippage and unexpected disturbances. When designing locomotion algorithms, this degradation can result in planned trajectories that are not consistent with the reality, if not dealt properly. In this work, we propose a heuristic-based planning approach that enables a quadruped robot to successfully traverse a significan…
In this work, we show how to learn a visual walking policy that only uses a monocular RGB camera and proprioception. Since simulating RGB is hard, we necessarily have to learn vision in the real world. We start with a blind walking policy trained in simulation. This policy can traverse some terrains in the real world but often struggles since it lacks knowledge of the upcoming geometry. This can be resolved with the use of vision. We train a visual module in the real world to predict the upcoming terrain with our proposed algorithm Cross-Modal Supervision (CMS). CMS uses time-shifted proprioce…
The semantics of the environment, such as the terrain type and property, reveals important information for legged robots to adjust their behaviors. In this work, we present a framework that learns semantics-aware locomotion skills from perception for quadrupedal robots, such that the robot can traverse through complex offroad terrains with appropriate speeds and gaits using perception information. Due to the lack of high-fidelity outdoor simulation, our framework needs to be trained directly in the real world, which brings unique challenges in data efficiency and safety. To ensure sample effic…
Despite many accomplishments by legged robot designers, state-of-the-art bipedal robots are prone to falling over, cannot negotiate extremely rough terrains and cannot directly regulate unilateral contact forces. Our objective is to integrate merits of legged and aerial robots in a single platform. We will show that the thrusters in a bipedal legged robot called Harpy can be leveraged to stabilize the robot's frontal dynamics and permit jumping over large obstacles which is an unusual capability not reported before. In addition, we will capitalize on the thrusters action in Harpy and will show…
Robots "in-the-wild" encounter and must traverse widely varying terrain, ranging from solid ground to granular materials like sand to full liquids. Numerous approaches exist, including wheeled and legged robots, each excelling in specific domains. Screw-based locomotion is a promising approach for multi-domain mobility, leveraged in exploratory robotic designs, including amphibious vehicles and snake robotics. However, unlike other forms of locomotion, there is a limited exploration of the models, parameter effects, and efficiency for multi-terrain Archimedes screw locomotion. In this work, we…
ATRos: Learning Energy-Efficient Agile Locomotion for Wheeled-legged Robots
Shanghai Huawei Technologies Co., Ltd.（上海华为技术有限公司）；College of Future Information Technology, Fudan University（复旦大学未来信息科技学院）；Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）；School of Aeronautic and Astronautics, Zhejiang University（浙江大学航空宇航学院）；School of Electronics and Communication Engineering, Sun Yat-sen University（中山大学电子与通信工程学院）
Istituto Italiano di Tecnologia（意大利理工学院）；University of Oxford（牛津大学）
Legged robots can outperform wheeled machines for most navigation tasks across unknown and rough terrains. For such tasks, visual feedback is a fundamental asset to provide robots with terrain-awareness. However, robust dynamic locomotion on difficult terrains with real-time performance guarantees remains a challenge. We present here a real-time, dynamic foothold adaptation strategy based on visual feedback. Our method adjusts the landing position of the feet in a fully reactive manner, using only on-board computers and sensors. The correction is computed and executed continuously along the sw…
Effect of Gait Design on Proprioceptive Sensing of Terrain Properties in a Quadrupedal Robot
Department of Mechanical Engineering, Massachusetts Institute of Technology（机械工程系，麻省理工学院）；Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California（Ming Hsieh 电子与计算机工程系，南加州大学）；Department of Earth and Environmental Science, University of Pennsylvania（地球与环境科学系，宾夕法尼亚大学）
本文对比四足机器人的Crawl N' Sense与Trot-Walk步态，证明慢速爬行步态能更稳定、准确地感知可变形地形强度及表面结壳破裂。
California Institute of Technology（加州理工学院）；ETH Zurich（苏黎世联邦理工学院）
Terrain-aware locomotion has become an emerging topic in legged robotics. However, it is hard to generate diverse, challenging, and realistic unstructured terrains in simulation, which limits the way researchers evaluate their locomotion policies. In this paper, we prototype the generation of a terrain dataset via terrain authoring and active learning, and the learned samplers can stably generate diverse high-quality terrains. We expect the generated dataset to make a terrain-robustness benchmark for legged locomotion. The dataset, the code implementation, and some policy evaluations are relea…
University of Edinburgh（爱丁堡大学）；University College London（伦敦大学学院）
To proactively navigate and traverse various terrains, active use of visual perception becomes indispensable. We aim to investigate the feasibility and performance of using sparse visual observations to achieve perceptual locomotion over a range of common terrains (steps, ramps, gaps, and stairs) in human-centered environments. We formulate a selection of sparse visual inputs suitable for locomotion over the terrains of interest, and propose a learning framework to integrate exteroceptive and proprioceptive states. We specifically design the state observations and a training curriculum to lear…
Dynamic quadruped locomotion over challenging terrains with precise foot placements is a hard problem for both optimal control methods and Reinforcement Learning (RL). Non-linear solvers can produce coordinated constraint satisfying motions, but often take too long to converge for online application. RL methods can learn dynamic reactive controllers but require carefully tuned shaping rewards to produce good gaits and can have trouble discovering precise coordinated movements. Imitation learning circumvents this problem and has been used with motion capture data to extract quadruped gaits for …
Whole-body Control (WBC) has emerged as an important framework in locomotion control for legged robots. However, most of WBC frameworks fail to generalize beyond rigid terrains. Legged locomotion over soft terrain is difficult due to the presence of unmodeled contact dynamics that WBCs do not account for. This introduces uncertainty in locomotion and affects the stability and performance of the system. In this paper, we propose a novel soft terrain adaptation algorithm called STANCE: Soft Terrain Adaptation and Compliance Estimation. STANCE consists of a WBC that exploits the knowledge of the …
Locomotion over soft terrain remains a challenging problem for legged robots. Most of the work done on state estimation for legged robots is designed for rigid contacts, and does not take into account the physical parameters of the terrain. That said, this letter answers the following questions: how and why does soft terrain affect state estimation for legged robots? To do so, we utilized a state estimator that fuses IMU measurements with leg odometry that is designed with rigid contact assumptions. We experimentally validated the state estimator with the HyQ robot trotting over both soft and …
Oxford Robotics Institute, University of Oxford（牛津大学牛津机器人研究所）
We present a unified model-based and data-driven approach for quadrupedal planning and control to achieve dynamic locomotion over uneven terrain. We utilize on-board proprioceptive and exteroceptive feedback to map sensory information and desired base velocity commands into footstep plans using a reinforcement learning (RL) policy. This RL policy is trained in simulation over a wide range of procedurally generated terrains. When ran online, the system tracks the generated footstep plans using a model-based motion controller. We evaluate the robustness of our method over a wide variety of compl…
Shanghai Jiao Tong University（上海交通大学）；Digital Brain Lab（数字大脑实验室）；ShanghaiTech University（上海科技大学）；University College London（伦敦大学学院）
Deep reinforcement learning has recently emerged as an appealing alternative for legged locomotion over multiple terrains by training a policy in physical simulation and then transferring it to the real world (i.e., sim-to-real transfer). Despite considerable progress, the capacity and scalability of traditional neural networks are still limited, which may hinder their applications in more complex environments. In contrast, the Transformer architecture has shown its superiority in a wide range of large-scale sequence modeling tasks, including natural language processing and decision-making pro…
CoRe-MoE: Contrastive Reweighted Mixture of Experts for Multi-Terrain Humanoid Locomotion with Gait Adaptation
Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；South China Agricultural University（华南农业大学）；Guangdong University of Technology（广东工业大学）
