Symmetry is a fundamental aspect of many real-world robotic tasks. However, current deep reinforcement learning (DRL) approaches can seldom harness and exploit symmetry effectively. Often, the learned behaviors fail to achieve the desired transformation invariances and suffer from motion artifacts. For instance, a quadruped may exhibit different gaits when commanded to move forward or backward, even though it is symmetrical about its torso. This issue becomes further pronounced in high-dimensional or complex environments, where DRL methods are prone to local optima and fail to explore regions of the state space equally. Past methods on encouraging symmetry for robotic tasks have studied this topic mainly in a single-task setting, where symmetry usually refers to symmetry in the motion, such as the gait patterns. In this paper, we revisit this topic for goal-conditioned tasks in robotics, where symmetry lies mainly in task execution and not necessarily in the learned motions themselves. In particular, we investigate two approaches to incorporate symmetry invariance into DRL -– data augmentation and mirror loss function. We provide a theoretical foundation for using augmented samples in an on-policy setting. Based on this, we show that the corresponding approach achieves faster convergence and improves the learned behaviors in various challenging robotic tasks, from climbing boxes with a quadruped to dexterous manipulation.

We present SpaceHopper, a three-legged, small-scale robot designed for future mobile exploration of asteroids and moons. The robot weighs 5.2 kg and has a body size of 245 mm while using space-qualifiable components. Furthermore, SpaceHopper’s design and controls make it well-adapted for investigating dynamic locomotion modes with extended flight-phases. Instead of gyroscopes or fly-wheels, the system uses its three legs to reorient the body during flight in preparation for landing. We control the leg motion for reorientation using Deep Reinforcement Learning policies. In a simulation of Ceres’ gravity (0.029 g), the robot can reliably jump to commanded positions up to 6 m away. Our real-world experiments show that SpaceHopper can successfully reorient to a safe landing orientation within 9.7 deg inside a rotational gimbal and jump in a counterweight setup in Earth’s gravity. Overall, we consider SpaceHopper an important step towards controlled jumping locomotion in low-gravity environments.

Autonomous robots must navigate reliably in unknown environments even under compromised exteroceptive perception, or perception failures. Such failures often occur when harsh environments lead to degraded sensing, or when the perception algorithm misinterprets the scene due to limited generalization. In this paper, we model perception failures as invisible obstacles and pits, and train a reinforcement learning (RL) based local navigation policy to guide our legged robot. Unlike previous works relying on heuristics and anomaly detection to update navigational information, we train our navigation policy to reconstruct the environment information in the latent space from corrupted perception and react to perception failures end-to-end. To this end, we incorporate both proprioception and exteroception into our policy inputs, thereby enabling the policy to sense collisions on different body parts and pits, prompting corresponding reactions. We validate our approach in simulation and on the real quadruped robot ANYmal running in real-time (<10ms CPU inference). In a quantitative comparison with existing heuristic-based locally reactive planners, our policy increases the success rate over 30% when facing perception failures. Project Page: https://bit.ly/45NBTuh.

Quadruped robots have shown remarkable mobility on various terrains through reinforcement learning. Yet, in the presence of sparse footholds and risky terrains such as stepping stones and balance beams, which require precise foot placement to avoid falls, model-based approaches are often used. In this paper, we show that end-to-end reinforcement learning can also enable the robot to traverse risky terrains with dynamic motions. To this end, our approach involves training a generalist policy for agile locomotion on disorderly and sparse stepping stones before transferring its reusable knowledge to various more challenging terrains by finetuning specialist policies from it. Given that the robot needs to rapidly adapt its velocity on these terrains, we formulate the task as a navigation task instead of the commonly used velocity tracking which constrains the robot’s behavior and propose an exploration strategy to overcome sparse rewards and achieve high robustness. We validate our proposed method through simulation and real-world experiments on an ANYmal-D robot achieving peak forward velocity of ≥2.5 m/s on sparse stepping stones and narrow balance beams. Video: youtu.be/Z5X0J8OH6z4

Reinforcement learning (RL) has emerged as a powerful approach for locomotion control of highly articulated robotic systems. However, one major challenge is the tedious process of tuning the reward function to achieve the desired motion style. To address this issue, imitation learning approaches such as adversarial motion priors have been proposed, which encourage a pre-defined motion style. In this work, we present an approach to enhance the concept of adversarial motion prior-based RL, allowing for multiple, discretely switchable motion styles. Our approach demonstrates that multiple styles and skills can be learned simultaneously without significant performance differences, even in combination with motion data-free skills. We conducted several real-world experiments using a wheeled-legged robot to validate our approach. The experiments involved learning skills from existing RL controllers and trajectory optimization, such as ducking and walking, as well as novel skills, such as switching between a quadrupedal and humanoid configuration. For the latter skill, the robot was required to stand up, navigate on two wheels, and sit down. Instead of manually tuning the sit-down motion, we found that a reverse playback of the stand-up movement helped the robot discover feasible sit-down behaviors and avoided the need for tedious reward function tuning.

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. Supplementary videos can be found on the project website: https://sites.google.com/leggedrobotics.com/end-to-end-loco-navigation

In this article, we show that learned policies can be applied to solve legged locomotion control tasks with extensive flight phases, such as those encountered in space exploration. Using an off-the-shelf deep reinforcement learning algorithm, we train a neural network to control a jumping quadruped robot while solely using its limbs for attitude control. We present tasks of increasing complexity leading to a combination of 3-D (re)orientation and landing locomotion behaviors of a quadruped robot traversing simulated low-gravity celestial bodies. We show that our approach easily generalizes across these tasks and successfully trains policies for each case. Using sim-to-real transfer, we deploy trained policies in the real world on the SpaceBok robot placed on an experimental testbed designed for 2-D microgravity experiments. The experimental results demonstrate that repetitive controlled jumping and landing with natural agility is possible.