Legged robots have the potential to traverse complex terrain and access confined spaces beyond the reach of traditional platforms thanks to their ability to carefully select footholds and flexibly adapt their body posture while walking. However, robust deployment in real-world applications is still an open challenge. In this paper, we present a method for legged locomotion control using reinforcement learning and 3D volumetric representations to enable robust and versatile locomotion in confined and unstructured environments. By employing a two-layer hierarchical policy structure, we exploit the capabilities of a highly robust low-level policy to follow 6D commands and a high-level policy to enable three-dimensional spatial awareness for navigating under overhanging obstacles. Our study includes the development of a procedural terrain generator to create diverse training environments. We present a series of experimental evaluations in both simulation and real-world settings, demonstrating the effectiveness of our approach in controlling a quadruped robot in confined, rough terrain. By achieving this, our work extends the applicability of legged robots to a broader range of scenarios.

Perceiving the surrounding environment is crucial for autonomous mobile robots. An elevation map provides a memory-efficient and simple yet powerful geometric represen-tation of the terrain for ground robots. The robots can use this information for navigation in an unknown environment or perceptive locomotion control over rough terrain. Depending on the application, various post processing steps may be incorpo-rated, such as smoothing, inpainting or plane segmentation. In this work, we present an elevation mapping pipeline leveraging GPU for fast and efficient processing with additional features both for navigation and locomotion. We demonstrated our map-ping framework through extensive hardware experiments. Our mapping software was successfully deployed for underground exploration during DARPA Subterranean Challenge and for various experiments of quadrupedal locomotion.

Navigating off-road with a fast autonomous vehicle depends on a robust perception system that differentiates traversable from non-traversable terrain. Typically, this depends on a semantic understanding which is based on supervised learning from images annotated by a human expert. This requires a significant investment in human time, assumes correct expert classification, and small details can lead to misclassification. To address these challenges, we propose a method for predicting high- and low-risk terrains from only past vehicle experience in a self-supervised fashion. First, we develop a tool that projects the vehicle trajectory into the front camera image. Second, occlusions in the 3D representation of the terrain are filtered out. Third, an autoencoder trained on masked vehicle trajectory regions identifies low- and high-risk terrains based on the reconstruction error. We evaluated our approach with two models and different bottleneck sizes with two different training and testing sites with a four-wheeled off-road vehicle. Comparison with two independent test sets of semantic labels from similar terrain as training sites demonstrates the ability to separate the ground as low-risk and the vegetation as high-risk with 81.1% and 85.1% accuracy.

Navigation on challenging terrain topographies requires the understanding of robots’ locomotion capabilities to produce optimal solutions. We present an integrated framework for real-time autonomous navigation of mobile robots based on elevation maps. The framework performs rapid global path planning and optimization that is aware of the locomotion capabilities of the robot. A GPU-aided, sampling-based path planner combined with a gradient-based path optimizer provides optimal paths by using a neural network-based locomotion cost predictor which is trained in simulation. We show that our approach is capable of planning and optimizing paths three orders of magnitude faster than RRT* on GPU-enabled hardware, enabling real-time deployment on mobile platforms. We successfully evaluate the framework on the ANYmal C quadrupedal robot in both simulations and real-world environments for path planning tasks on multiple complex terrains.

Navigation planning for legged robots has distinct challenges compared to wheeled and tracked systems due to the ability to lift legs off the ground and step over obstacles. While most navigation planners assume a fixed traversability value for a single terrain patch, we overcome this limitation by proposing a reachability-based navigation planner for legged robots. We approximate the robot morphology by a set of reachability and body volumes, assuming that the reachability volumes need to always be in contact with the environment, while the body should be contact-free. We train a convolutional neural network to predict foothold scores which are used to restrict geometries which are considered suitable to step on. Using this representation, we propose a navigation planner based on probabilistic roadmaps. Through validation of only low-cost graph edges during graph expansion and an adaptive sampling scheme based on roadmap node density, we achieve real-time performance with fast update rates even in cluttered and narrow environments. We thoroughly validate the proposed navigation planner in simulation and demonstrate its performance in real-world experiments on the quadruped ANYmal.

Mobile robots are becoming very popular in real-world outdoors applications, where there are many challenges in robot control and perception. One of the most critical problems is to characterise the terrain traversed by the robot. This knowledge is indispensable for optimal terrain negotiation. Currently, most approaches are performing terrain classification from vision, but there is not enough research on terrain identification from a direct interaction of the robot with the environment. In our work, we proposed new methods for classification of force/torque data from an interaction of the legged robot foot with the ground, gathered during the walking process. We provided machine learning methods for terrain classification from raw force/torque signals for which we achieved 93% accuracy on a challenging dataset with 160 minutes of recorded fixed-length steps. We also worked on a dataset where the assumption of a fixed-length step is not valid. In this case, the final result is around 80% of accuracy. The most important fact is that the data in both cases was recorded while the robot was walking, no particular movements or controlled environment were needed. Additionally, we also proposed a clustering method which allows us to learn about the class membership based on the recorded data only, without any human supervision.

The high agility of legged systems allows them to operate in rugged outdoor environments. In these situations, knowledge about the terrain geometry is key for foothold planning to enable safe locomotion. However, on penetrable or highly compliant terrain (e.g. grass) the visibility of the supporting ground surface is obstructed, i.e. it cannot directly be perceived by depth sensors. We present a method to estimate the underlying terrain topography by fusing haptic information about foot contact closure locations with exteroceptive sensing. To obtain a dense support surface estimate from sparsely sampled footholds we apply Gaussian process regression. Exteroceptive information is integrated into the support surface estimation procedure by estimating the height of the penetrable surface layer from discrete penetration depth measurements at the footholds. The method is designed such that it provides a continuous support surface estimate even if there is only partial exteroceptive information available due to shadowing effects. Field experiments with the quadrupedal robot ANYmal show how the robot can smoothly and safely navigate in dense vegetation.

Current traffic rule handling in autonomous driving relies on non-scalable methods such as explicitly hard-coding sets of logical statements to evaluate rules. This is sufficient for early prototypes but is not scalable for larger systems designed to work in arbitrary locations. Such methods can also become problematic when traversing different geographical entities with changing traffic rules. Additionally, they do not adequately convey the uncertainty of the traffic rule evaluation stemming from uncertainty in sensor measurements. We propose an exchangeable traffic rules module which takes a knowledge base of sentences in first-order logic as input. These sentences consist of a limited number of high-level queries which are independent of local jurisdiction (e.g. can I turn right?). The knowledge base is then compiled into a potentially large logic graph. However, only a relatively small subset of the knowledge base is relevant for specific road geometries (e.g. some of the rules applicable to an intersection is not relevant for a T-junction). Since detailed road maps are available for autonomous driving, this information can be used to resolve these subsets in the knowledge base which only require map knowledge. Therefore, map information can be used to convert a single, large logic graph into a set of smaller, map-optimized logic graphs pruned for specific road geometries. The optimized graphs are then converted into Bayesian networks to facilitate probabilistic inference. Experiments were conducted using a traffic and scenario simulation framework. The results demonstrate a significant improvement in performance when using map-optimized logic graphs over a traditional first-order logic knowledge base.