Deep Measurement Updates for Bayes Filters

Measurement update rules for Bayes filters often contain hand-crafted heuristics to compute observation probabilities for high-dimensional sensor data, like images. In this work, we propose the novel approach Deep Measurement Update (DMU) as a general update rule for a wide range of systems. DMU has a conditional encoder-decoder neural network structure to process depth images as raw inputs. Even though the network is trained only on synthetic data, the model shows good performance at evaluation time on real-world data. With our proposed training scheme primed data training , we demonstrate how the DMU models can be trained efficiently to be sensitive to condition variables without having to rely on a stochastic information bottleneck. We validate the proposed methods in multiple scenarios of increasing complexity, beginning with the pose estimation of a single object to the joint estimation of the pose and the internal state of an articulated system. Moreover, we provide a benchmark against Articulated Signed Distance Functions(A-SDF) on the RBO dataset as a baseline comparison for articulation state estimation.

Autonomous Teamed Exploration of Subterranean Environments using Legged and Aerial Robots

This paper presents a novel strategy for autonomous teamed exploration of subterranean environments using legged and aerial robots. Tailored to the fact that subterranean settings, such as cave networks and underground mines, often involve complex, large-scale and multi-branched topologies, while wireless communication within them can be particularly challenging, this work is structured around the synergy of an onboard exploration path planner that allows for resilient long-term autonomy, and a multi-robot coordination framework. The onboard path planner is unified across legged and flying robots and enables navigation in environments with steep slopes, and diverse geometries. When a communication link is available, each robot of the team shares submaps to a centralized location where a multi-robot coordination framework identifies global frontiers of the exploration space to inform each system about where it should re-position to best continue its mission. The strategy is verified through a field deployment inside an underground mine in Switzerland using a legged and a flying robot collectively exploring for 45 min, as well as a longer simulation study with three systems.

Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning

In this work, we present and study a training set-up that achieves fast policy generation for real-world robotic tasks by using massive parallelism on a single workstation GPU. We analyze and discuss the impact of different training algorithm components in the massively parallel regime on the final policy performance and training times. In addition, we present a novel game-inspired curriculum that is well suited for training with thousands of simulated robots in parallel. We evaluate the approach by training the quadrupedal robot ANYmal to walk on challenging terrain. The parallel approach allows training policies for flat terrain in under four minutes, and in twenty minutes for uneven terrain. This represents a speedup of multiple orders of magnitude compared to previous work. Finally, we transfer the policies to the real robot to validate the approach. We open-source our training code to help accelerate further research in the field of learned legged locomotion.

Solving Occlusion in Terrain Mapping with Neural Networks

Accurate and complete terrain maps enhance the awareness of autonomous robots and enable safe and optimal path planning. Rocks and topography often create occlusions and lead to missing elevation information in the Digital Elevation Map (DEM). Currently, mostly traditional inpainting techniques based on diffusion or patch-matching are used by autonomous mobile robots to fill-in incomplete DEMs. These methods cannot leverage the high-level terrain characteristics and the geometric constraints of line of sight we humans use intuitively to predict occluded areas. We propose to use neural networks to reconstruct the occluded areas in DEMs. We introduce a self-supervised learning approach capable of training on real-world data without a need for ground-truth information. We accomplish this by adding artificial occlusion to the incomplete elevation maps constructed on a real robot by performing ray casting. We first evaluate a supervised learning approach on synthetic data for which we have the full ground-truth available and subsequently move to several real-world datasets. These real-world datasets were recorded during autonomous exploration of both structured and unstructured terrain with a legged robot, and additionally in a planetary scenario on Lunar analogue terrain. We state a significant improvement compared to the Telea and Navier-Stokes baseline methods both on synthetic terrain and for the real-world datasets. Our neural network is able to run in real-time on both CPU and GPU with suitable sampling rates for autonomous ground robots.

Passivity-based control for haptic teleoperation of a legged manipulator in presence of time-delays

When dealing with the haptic teleoperation of multi-limbed mobile manipulators, the problem of mitigating the destabilizing effects arising from the communication link between the haptic device and the remote robot has not been properly addressed. In this work, we propose a passive control architecture to haptically teleoperate a legged mobile manipulator, while remaining stable in the presence of time delays and frequency mismatches in the master and slave controllers. At the master side, a discrete-time energy modulation of the control input is proposed. At the slave side, passivity constraints are included in an optimization-based whole-body controller to satisfy the energy limitations. A hybrid teleoperation scheme allows the human operator to remotely operate the robot's end-effector while in stance mode, and its base velocity in locomotion mode. The resulting control architecture is demonstrated on a quadrupedal robot with an artificial delay added to the network.

Cat-like Jumping and Landing of Legged Robots in Low-gravity Using Deep Reinforcement Learning

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 trained 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 three-dimensional (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 two-dimensional micro-gravity experiments. The experimental results demonstrate that repetitive, controlled jumping and landing with natural agility is possible.

HEAP -- The autonomous walking excavator

The demand and the potential for automation in the construction sector is unmatched, particularly for increasing environmental sustainability, improving worker safety and reducing labor shortages. We have developed an autonomous walking excavator - based one of the most versatile machines found on construction sites - as one way to begin fulfilling this potential. This article describes the process of converting an off-the-shelf construction machine into an autonomous robotic system. First we outline the necessary sensing equipment for full autonomy and the novel actuation of the legs, and compare three different complementary actuation principles for the excavator's arm. Second, we solve the state estimation problem for a general wheeled-legged robot. Beside kinematic measurements, it includes GNSS-RTK, to absolutely reference the machine on a construction site. Third, we developed individual controllers for driving, chassis balancing and arm motions allowing for fully autonomous operation. Lastly, we highlight the machine's potential in four different real-world applications, e.g. autonomous trench digging, autonomous assembly of dry stone walls, autonomous forestry work and semi-autonomous teleoperation. On top, we also share some development insights and possible future research directions.

Model Predictive Robot-Environment Interaction Control for Mobile Manipulation Tasks

Modern, torque-controlled service robots can regulate contact forces when interacting with their environment. Model Predictive Control (MPC) is a powerful method to solve the underlying control problem, allowing to plan for whole-body motions while including different constraints imposed by the robot dynamics or its environment. However, an accurate model of the robot-environment is needed to achieve a satisfying closed-loop performance. Currently, this necessity undermines the performance and generality of MPC in manipulation tasks. In this work, we combine an MPC-based whole-body controller with two adaptive schemes, derived from online system identification and adaptive control. As a result, we enable a general mobile manipulator to interact with unknown environments, without any need for re-tuning parameters or pre-modeling the interacting objects. In combination with the MPC controller, the two adaptive approaches are validated and benchmarked with a ball-balancing manipulator in door opening and object lifting tasks.

Traversing Steep and Granular Martian Analog Slopes With a Dynamic Quadrupedal Robot

Celestial bodies such as the Moon and Mars are mainly covered by loose, granular soil, a notoriously challenging terrain to traverse with (wheeled) robotic systems. Here, we present experimental work on traversing steep, granular slopes with the dynamically walking quadrupedal robot SpaceBok. To adapt to the challenging environment, we developed passive-adaptive planar feet and optimized grouser pads to reduce sinkage and increase traction on planar and inclined granular soil. Single-foot experiments revealed that a large surface area of 110cm2 per foot reduces sinkage to an acceptable level even on highly collapsible soil (ES-1). Implementing several 12mm grouser blades increases traction by 22% to 66% on granular media compared to grouser-less designs. Together with a terrain-adapting walking controller, we validate - for the first time - static and dynamic locomotion on Mars analog slopes of up to 25{\deg}(the maximum of the testbed). We evaluated the performance between point- and planar feet and static and dynamic gaits regarding stability (safety), velocity, and energy consumption. We show that dynamic gaits are energetically more efficient than static gaits but are riskier on steep slopes. Our tests also revealed that planar feet's energy consumption drastically increases when the slope inclination approaches the soil's angle of internal friction due to shearing. Point feet are less affected by slippage due to their excessive sinkage, but in turn, are prone to instabilities and tripping. We present and discuss safe and energy-efficient global path-planning strategies for accessing steep topography on Mars based on our findings.

Generating Continuous Motion and Force Plans in Real-Time for Legged Mobile Manipulation

Manipulators can be added to legged robots, allowing them to interact with and change their environment. Legged mobile manipulation planners must consider how contact forces generated by these manipulators affect the system. Current planning strategies either treat these forces as immutable during planning or are unable to optimize over these contact forces while operating in real-time. This paper presents the Stability and Task Oriented Receding-Horizon Motion and Manipulation Autonomous Planner (STORMMAP) that is able to generate continuous plans for the robot's motion and manipulation force trajectories that ensure dynamic feasibility and stability of the platform, and incentivizes accomplishing manipulation and motion tasks specified by a user. STORMMAP uses a nonlinear optimization problem to compute these plans and is able to run in real-time by assuming contact locations are given a-priori, either by a user or an external algorithm. A variety of simulated experiments on a quadruped with a manipulator mounted to its torso demonstrate the versatility of STORMMAP. In contrast to existing state of the art methods, the approach described in this paper generates continuous plans in under ten milliseconds, an order of magnitude faster than previous strategies.