arXiv subjects

Marco Hutter

Publications and source records attributed to Marco Hutter.

At least 199 records · Page 11Linked to original sources

arXiv2023

ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots

Performing agile navigation with four-legged robots is a challenging task due to the highly dynamic motions, contacts with various parts of the robot, and the limited field of view of the perception sensors. In this paper, we propose a fully-learned approach to train such robots and conquer scenarios that are reminiscent of parkour challenges. The method involves training advanced locomotion skills for several types of obstacles, such as walking, jumping, climbing, and crouching, and then using a high-level policy to select and control those skills across the terrain. Thanks to our hierarchical formulation, the navigation policy is aware of the capabilities of each skill, and it will adapt its behavior depending on the scenario at hand. Additionally, a perception module is trained to reconstruct obstacles from highly occluded and noisy sensory data and endows the pipeline with scene understanding. Compared to previous attempts, our method can plan a path for challenging scenarios without expert demonstration, offline computation, a priori knowledge of the environment, or taking contacts explicitly into account. While these modules are trained from simulated data only, our real-world experiments demonstrate successful transfer on hardware, where the robot navigates and crosses consecutive challenging obstacles with speeds of up to two meters per second. The supplementary video can be found on the project website: https://sites.google.com/leggedrobotics.com/agile-navigation

cs.RO↗

arXiv2023

SMUG Planner: A Safe Multi-Goal Planner for Mobile Robots in Challenging Environments

Robotic exploration or monitoring missions require mobile robots to autonomously and safely navigate between multiple target locations in potentially challenging environments. Currently, this type of multi-goal mission often relies on humans designing a set of actions for the robot to follow in the form of a path or waypoints. In this work, we consider the multi-goal problem of visiting a set of pre-defined targets, each of which could be visited from multiple potential locations. To increase autonomy in these missions, we propose a safe multi-goal (SMUG) planner that generates an optimal motion path to visit those targets. To increase safety and efficiency, we propose a hierarchical state validity checking scheme, which leverages robot-specific traversability learned in simulation. We use LazyPRM* with an informed sampler to accelerate collision-free path generation. Our iterative dynamic programming algorithm enables the planner to generate a path visiting more than ten targets within seconds. Moreover, the proposed hierarchical state validity checking scheme reduces the planning time by 30% compared to pure volumetric collision checking and increases safety by avoiding high-risk regions. We deploy the SMUG planner on the quadruped robot ANYmal and show its capability to guide the robot in multi-goal missions fully autonomously on rough terrain.

cs.RO↗

arXiv2023

iPlanner: Imperative Path Planning

The problem of path planning has been studied for years. Classic planning pipelines, including perception, mapping, and path searching, can result in latency and compounding errors between modules. While recent studies have demonstrated the effectiveness of end-to-end learning methods in achieving high planning efficiency, these methods often struggle to match the generalization abilities of classic approaches in handling different environments. Moreover, end-to-end training of policies often requires a large number of labeled data or training iterations to reach convergence. In this paper, we present a novel Imperative Learning (IL) approach. This approach leverages a differentiable cost map to provide implicit supervision during policy training, eliminating the need for demonstrations or labeled trajectories. Furthermore, the policy training adopts a Bi-Level Optimization (BLO) process, which combines network update and metric-based trajectory optimization, to generate a smooth and collision-free path toward the goal based on a single depth measurement. The proposed method allows task-level costs of predicted trajectories to be backpropagated through all components to update the network through direct gradient descent. In our experiments, the method demonstrates around 4x faster planning than the classic approach and robustness against localization noise. Additionally, the IL approach enables the planner to generalize to various unseen environments, resulting in an overall 26-87% improvement in SPL performance compared to baseline learning methods.

cs.RO↗

arXiv2023

Fast Traversability Estimation for Wild Visual Navigation

Natural environments such as forests and grasslands are challenging for robotic navigation because of the false perception of rigid obstacles from high grass, twigs, or bushes. In this work, we propose Wild Visual Navigation (WVN), an online self-supervised learning system for traversability estimation which uses only vision. The system is able to continuously adapt from a short human demonstration in the field. It leverages high-dimensional features from self-supervised visual transformer models, with an online scheme for supervision generation that runs in real-time on the robot. We demonstrate the advantages of our approach with experiments and ablation studies in challenging environments in forests, parks, and grasslands. Our system is able to bootstrap the traversable terrain segmentation in less than 5 min of in-field training time, enabling the robot to navigate in complex outdoor terrains - negotiating obstacles in high grass as well as a 1.4 km footpath following. While our experiments were executed with a quadruped robot, ANYmal, the approach presented can generalize to any ground robot.

cs.RO↗

arXiv2023

Seeing Through the Grass: Semantic Pointcloud Filter for Support Surface Learning

Mobile ground robots require perceiving and understanding their surrounding support surface to move around autonomously and safely. The support surface is commonly estimated based on exteroceptive depth measurements, e.g., from LiDARs. However, the measured depth fails to align with the true support surface in the presence of high grass or other penetrable vegetation. In this work, we present the Semantic Pointcloud Filter (SPF), a Convolutional Neural Network (CNN) that learns to adjust LiDAR measurements to align with the underlying support surface. The SPF is trained in a semi-self-supervised manner and takes as an input a LiDAR pointcloud and RGB image. The network predicts a binary segmentation mask that identifies the specific points requiring adjustment, along with estimating their corresponding depth values. To train the segmentation task, 300 distinct images are manually labeled into rigid and non-rigid terrain. The depth estimation task is trained in a self-supervised manner by utilizing the future footholds of the robot to estimate the support surface based on a Gaussian process. Our method can correctly adjust the support surface prior to interacting with the terrain and is extensively tested on the quadruped robot ANYmal. We show the qualitative benefits of SPF in natural environments for elevation mapping and traversability estimation compared to using raw sensor measurements and existing smoothing methods. Quantitative analysis is performed in various natural environments, and an improvement by 48% RMSE is achieved within a meadow terrain.

cs.RO↗

arXiv2023

Event-based Agile Object Catching with a Quadrupedal Robot

Quadrupedal robots are conquering various indoor and outdoor applications due to their ability to navigate challenging uneven terrains. Exteroceptive information greatly enhances this capability since perceiving their surroundings allows them to adapt their controller and thus achieve higher levels of robustness. However, sensors such as LiDARs and RGB cameras do not provide sufficient information to quickly and precisely react in a highly dynamic environment since they suffer from a bandwidth-latency tradeoff. They require significant bandwidth at high frame rates while featuring significant perceptual latency at lower frame rates, thereby limiting their versatility on resource-constrained platforms. In this work, we tackle this problem by equipping our quadruped with an event camera, which does not suffer from this tradeoff due to its asynchronous and sparse operation. In leveraging the low latency of the events, we push the limits of quadruped agility and demonstrate high-speed ball catching for the first time. We show that our quadruped equipped with an event camera can catch objects with speeds up to 15 m/s from 4 meters, with a success rate of 83%. Using a VGA event camera, our method runs at 100 Hz on an NVIDIA Jetson Orin.

cs.RO↗

arXiv2023

Design and Motion Planning for a Reconfigurable Robotic Base

A robotic platform for mobile manipulation needs to satisfy two contradicting requirements for many real-world applications: A compact base is required to navigate through cluttered indoor environments, while the support needs to be large enough to prevent tumbling or tip over, especially during fast manipulation operations with heavy payloads or forceful interaction with the environment. This paper proposes a novel robot design that fulfills both requirements through a versatile footprint. It can reconfigure its footprint to a narrow configuration when navigating through tight spaces and to a wide stance when manipulating heavy objects. Furthermore, its triangular configuration allows for high-precision tasks on uneven ground by preventing support switches. A model predictive control strategy is presented that unifies planning and control for simultaneous navigation, reconfiguration, and manipulation. It converts task-space goals into whole-body motion plans for the new robot. The proposed design has been tested extensively with a hardware prototype. The footprint reconfiguration allows to almost completely remove manipulation-induced vibrations. The control strategy proves effective in both lab experiment and during a real-world construction task.

cs.RO↗

arXiv2023

PyPose: A Library for Robot Learning with Physics-based Optimization

Deep learning has had remarkable success in robotic perception, but its data-centric nature suffers when it comes to generalizing to ever-changing environments. By contrast, physics-based optimization generalizes better, but it does not perform as well in complicated tasks due to the lack of high-level semantic information and reliance on manual parametric tuning. To take advantage of these two complementary worlds, we present PyPose: a robotics-oriented, PyTorch-based library that combines deep perceptual models with physics-based optimization. PyPose's architecture is tidy and well-organized, it has an imperative style interface and is efficient and user-friendly, making it easy to integrate into real-world robotic applications. Besides, it supports parallel computing of any order gradients of Lie groups and Lie algebras and $2^{\text{nd}}$-order optimizers, such as trust region methods. Experiments show that PyPose achieves more than $10\times$ speedup in computation compared to the state-of-the-art libraries. To boost future research, we provide concrete examples for several fields of robot learning, including SLAM, planning, control, and inertial navigation.

cs.RO↗

arXiv2023

Bayesian Multi-Task Learning MPC for Robotic Mobile Manipulation

Mobile manipulation in robotics is challenging due to the need of solving many diverse tasks, such as opening a door or picking-and-placing an object. Typically, a basic first-principles system description of the robot is available, thus motivating the use of model-based controllers. However, the robot dynamics and its interaction with an object are affected by uncertainty, limiting the controller's performance. To tackle this problem, we propose a Bayesian multi-task learning model that uses trigonometric basis functions to identify the error in the dynamics. In this way, data from different but related tasks can be leveraged to provide a descriptive error model that can be efficiently updated online for new, unseen tasks. We combine this learning scheme with a model predictive controller, and extensively test the effectiveness of the proposed approach, including comparisons with available baseline controllers. We present simulation tests with a ball-balancing robot, and door-opening hardware experiments with a quadrupedal manipulator.

cs.RO↗

arXiv2023

Learning Arm-Assisted Fall Damage Reduction and Recovery for Legged Mobile Manipulators

Adaptive falling and recovery skills greatly extend the applicability of robot deployments. In the case of legged mobile manipulators, the robot arm could adaptively stop the fall and assist the recovery. Prior works on falling and recovery strategies for legged mobile manipulators usually rely on assumptions such as inelastic collisions and falling in defined directions to enable real-time computation. This paper presents a learning-based approach to reducing fall damage and recovery. An asymmetric actor-critic training structure is used to train a time-invariant policy with time-varying reward functions. In simulated experiments, the policy recovers from 98.9\% of initial falling configurations. It reduces base contact impulse, peak joint internal forces, and base acceleration during the fall compared to the baseline methods. The trained control policy is deployed and extensively tested on the ALMA robot hardware. A video summarizing the proposed method and the hardware tests is available at https://youtu.be/avwg2HqGi8s.

cs.RO↗

arXiv2023

ArtPlanner: Robust Legged Robot Navigation in the Field

Due to the highly complex environment present during the DARPA Subterranean Challenge, all six funded teams relied on legged robots as part of their robotic team. Their unique locomotion skills of being able to step over obstacles require special considerations for navigation planning. In this work, we present and examine ArtPlanner, the navigation planner used by team CERBERUS during the Finals. It is based on a sampling-based method that determines valid poses with a reachability abstraction and uses learned foothold scores to restrict areas considered safe for stepping. The resulting planning graph is assigned learned motion costs by a neural network trained in simulation to minimize traversal time and limit the risk of failure. Our method achieves real-time performance with a bounded computation time. We present extensive experimental results gathered during the Finals event of the DARPA Subterranean Challenge, where this method contributed to team CERBERUS winning the competition. It powered navigation of four ANYmal quadrupeds for 90 minutes of autonomous operation without a single planning or locomotion failure.

cs.RO↗

arXiv2023

Learning-based Design and Control for Quadrupedal Robots with Parallel-Elastic Actuators

Parallel-elastic joints can improve the efficiency and strength of robots by assisting the actuators with additional torques. For these benefits to be realized, a spring needs to be carefully designed. However, designing robots is an iterative and tedious process, often relying on intuition and heuristics. We introduce a design optimization framework that allows us to co-optimize a parallel elastic knee joint and locomotion controller for quadrupedal robots with minimal human intuition. We design a parallel elastic joint and optimize its parameters with respect to the efficiency in a model-free fashion. In the first step, we train a design-conditioned policy using model-free Reinforcement Learning, capable of controlling the quadruped in the predefined range of design parameters. Afterwards, we use Bayesian Optimization to find the best design using the policy. We use this framework to optimize the parallel-elastic spring parameters for the knee of our quadrupedal robot ANYmal together with the optimal controller. We evaluate the optimized design and controller in real-world experiments over various terrains. Our results show that the new system improves the torque-square efficiency of the robot by 33% compared to the baseline and reduces maximum joint torque by 30% without compromising tracking performance. The improved design resulted in 11% longer operation time on flat terrain.

cs.RO↗

arXiv2022

Planar Bipedal Locomotion with Nonlinear Model Predictive Control: Online Gait Generation using Whole-Body Dynamics

The ability to generate dynamic walking in real-time for bipedal robots with input constraints and underactuation has the potential to enable locomotion in dynamic, complex and unstructured environments. Yet, the high-dimensional nature of bipedal robots has limited the use of full-order rigid body dynamics to gaits which are synthesized offline and then tracked online. In this work we develop an online nonlinear model predictive control approach that leverages the full-order dynamics to realize diverse walking behaviors. Additionally, this approach can be coupled with gaits synthesized offline via a desired reference to enable a shorter prediction horizon and rapid online re-planning, bridging the gap between online reactive control and offline gait planning. We demonstrate the proposed method, both with and without an offline gait, on the planar robot AMBER-3M in simulation and on hardware.

cs.RO↗

arXiv2022

A Framework for Collaborative Multi-Robot Mapping using Spectral Graph Wavelets

The exploration of large-scale unknown environments can benefit from the deployment of multiple robots for collaborative mapping. Each robot explores a section of the environment and communicates onboard pose estimates and maps to a central server to build an optimized global multi-robot map. Naturally, inconsistencies can arise between onboard and server estimates due to onboard odometry drift, failures, or degeneracies. The mapping server can correct and overcome such failure cases using computationally expensive operations such as inter-robot loop closure detection and multi-modal mapping. However, the individual robots do not benefit from the collaborative map if the mapping server provides no feedback. Although server updates from the multi-robot map can greatly alleviate the robotic mission strategically, most existing work lacks them, due to their associated computational and bandwidth-related costs. Motivated by this challenge, this paper proposes a novel collaborative mapping framework that enables global mapping consistency among robots and the mapping server. In particular, we propose graph spectral analysis, at different spatial scales, to detect structural differences between robot and server graphs, and to generate necessary constraints for the individual robot pose graphs. Our approach specifically finds the nodes that correspond to the drift's origin rather than the nodes where the error becomes too large. We thoroughly analyze and validate our proposed framework using several real-world multi-robot field deployments where we show improvements of the onboard system up to 90\% and can recover the onboard estimation from localization failures and even from the degeneracies within its estimation.

cs.RO↗

arXiv2022

LiDAR-guided object search and detection in Subterranean Environments

Detecting objects of interest, such as human survivors, safety equipment, and structure access points, is critical to any search-and-rescue operation. Robots deployed for such time-sensitive efforts rely on their onboard sensors to perform their designated tasks. However, as disaster response operations are predominantly conducted under perceptually degraded conditions, commonly utilized sensors such as visual cameras and LiDARs suffer in terms of performance degradation. In response, this work presents a method that utilizes the complementary nature of vision and depth sensors to leverage multi-modal information to aid object detection at longer distances. In particular, depth and intensity values from sparse LiDAR returns are used to generate proposals for objects present in the environment. These proposals are then utilized by a Pan-Tilt-Zoom (PTZ) camera system to perform a directed search by adjusting its pose and zoom level for performing object detection and classification in difficult environments. The proposed work has been thoroughly verified using an ANYmal quadruped robot in underground settings and on datasets collected during the DARPA Subterranean Challenge finals.

cs.RO↗

arXiv2022

Meta Reinforcement Learning for Optimal Design of Legged Robots

The process of robot design is a complex task and the majority of design decisions are still based on human intuition or tedious manual tuning. A more informed way of facing this task is computational design methods where design parameters are concurrently optimized with corresponding controllers. Existing approaches, however, are strongly influenced by predefined control rules or motion templates and cannot provide end-to-end solutions. In this paper, we present a design optimization framework using model-free meta reinforcement learning, and its application to the optimizing kinematics and actuator parameters of quadrupedal robots. We use meta reinforcement learning to train a locomotion policy that can quickly adapt to different designs. This policy is used to evaluate each design instance during the design optimization. We demonstrate that the policy can control robots of different designs to track random velocity commands over various rough terrains. With controlled experiments, we show that the meta policy achieves close-to-optimal performance for each design instance after adaptation. Lastly, we compare our results against a model-based baseline and show that our approach allows higher performance while not being constrained by predefined motions or gait patterns.

cs.RO↗

arXiv2022

Advanced Skills by Learning Locomotion and Local Navigation End-to-End

The common approach for local navigation on challenging environments with legged robots requires path planning, path following and locomotion, which usually requires a locomotion control policy that accurately tracks a commanded velocity. However, by breaking down the navigation problem into these sub-tasks, we limit the robot's capabilities since the individual tasks do not consider the full solution space. In this work, we propose to solve the complete problem by training an end-to-end policy with deep reinforcement learning. Instead of continuously tracking a precomputed path, the robot needs to reach a target position within a provided time. The task's success is only evaluated at the end of an episode, meaning that the policy does not need to reach the target as fast as possible. It is free to select its path and the locomotion gait. Training a policy in this way opens up a larger set of possible solutions, which allows the robot to learn more complex behaviors. We compare our approach to velocity tracking and additionally show that the time dependence of the task reward is critical to successfully learn these new behaviors. Finally, we demonstrate the successful deployment of policies on a real quadrupedal robot. The robot is able to cross challenging terrains, which were not possible previously, while using a more energy-efficient gait and achieving a higher success rate.

cs.RO↗

arXiv2022

Locomotion Policy Guided Traversability Learning using Volumetric Representations of Complex Environments

Despite the progress in legged robotic locomotion, autonomous navigation in unknown environments remains an open problem. Ideally, the navigation system utilizes the full potential of the robots' locomotion capabilities while operating within safety limits under uncertainty. The robot must sense and analyze the traversability of the surrounding terrain, which depends on the hardware, locomotion control, and terrain properties. It may contain information about the risk, energy, or time consumption needed to traverse the terrain. To avoid hand-crafted traversability cost functions we propose to collect traversability information about the robot and locomotion policy by simulating the traversal over randomly generated terrains using a physics simulator. Thousand of robots are simulated in parallel controlled by the same locomotion policy used in reality to acquire 57 years of real-world locomotion experience equivalent. For deployment on the real robot, a sparse convolutional network is trained to predict the simulated traversability cost, which is tailored to the deployed locomotion policy, from an entirely geometric representation of the environment in the form of a 3D voxel-occupancy map. This representation avoids the need for commonly used elevation maps, which are error-prone in the presence of overhanging obstacles and multi-floor or low-ceiling scenarios. The effectiveness of the proposed traversability prediction network is demonstrated for path planning for the legged robot ANYmal in various indoor and natural environments.

cs.RO↗