Intelligent robotic coworkers are considered a valuable addition in many application areas. This applies not only to terrestrial domains, but also to the exploration of our solar system. As humankind moves toward an ever increasing presence in space, infrastructure has to be constructed and maintained on distant planets such as Mars. AI-enabled robots will play a major role in this scenario. The space agencies envisage robotic co-workers to be deployed to set-up habitats, energy, and return vessels for future human scientists. By leveraging AI planning methods, this vision has already become one step closer to reality. In the METERON SUPVIS Justin experiment, the intelligent robotic coworker Rollin’ Justin was controlled from Astronauts aboard the International Space Station (ISS) in order to maintain a Martian mock-up solar panel farm located on Earth to demonstrate the technology readiness of the developed methods. For this work, the system is demonstrated at AAAI 2019, controlling Rollin’ Justin located in Munich, Germany from Honolulu, Hawaii.

The paper addresses the static balancing and walking of elastically actuated legged robots. The control is realized by commanding the motor positions only and exploiting the bijective relation between motor and link positions at equilibrium under static external forces. The approach is formulated in a quite general framework first. The main implementation contribution is the definition of a body coordinate system and of an appropriate set of constraints, which leads to a fully determined system of equations. In addition to the desired COM and the vertical foot positions, which are defined by the walking task and the terrain, the imposed constraints are related to distances between individual legs. The controller is experimentally validated on a compliantly actuated quadruped.

This paper presents the first two members of the new generation of CLASH hands, which exploit low cost actuation and rapid prototyping to create antagonistic modular and lightweight hands and grippers. The hands approach the robustness of the DLR Awiwi hand with a much lower complexity and cost. To reduce the number of required actuators, a differential coupling mechanism for underactuated fingers was developed, along with a new mechanism that uses variable stiffness actuation in order to increase the workspace of underactuated fingers. The hands provide a research platform for both hand-in-hand and robotic grasping. Design aspects are discussed, and an initial experimental validation verifies the hands' performance.

Generalising dexterous grasps to novel objects is an open problem. We show how to learn grasps for high DoF hands that generalise to novel objects, given as little as one demonstrated grasp. During grasp learning two types of probability density are learned that model the demonstrated grasp. The first density type (the contact model) models the relationship of an individual finger part to local surface features at its contact point. The second density type (the hand configuration model) models the whole hand configuration during the approach to grasp. When presented with a new object, many candidate grasps are generated, and a kinematically feasible grasp is selected that maximises the product of these densities. We demonstrate 31 successful grasps on novel objects (an 86% success rate), transferred from 16 training grasps. The method enables: transfer of dexterous grasps within object categories; across object categories; to and from objects where there is no complete model of the object available; and using two different dexterous hands.

Many houseworks such as cleaning the floor or wiping the windows require to manipulate tools over wide areas. It is necessary to move along a path while manipulating a tool with the whole body and applying exactly the right amount of force to successfully accomplish the task. So mastering such a challenge demands detailed knowledge about the involved objects and the underlying process models. Reasoning about an appropriate parameterization of the task is thereby essential. In this paper we propose a combination of object-centered hybrid reasoning and compliant force control to solve complex whole-body mobile manipulation issues. Depending on the objects involved in the task, an appropriate controller is selected and automatically parameterized. The methods are validated in an elaborate experiment on the humanoid robot Rollin' Justin.

Dexterous manipulation of everyday objects requires a precise tactile sense. Slip detection is mandatory to overcome uncertainty and compensate for external disturbances. We compare three different approaches for detecting slip. The methods are model-based slip detection via friction cones, vibration-based detection via bandpass filtering, and a common learning algorithm. They are implemented and tested on a tendon-driven two-finger setup equipped with two tactile BioTac®sensors. Several experiments are conducted to evaluate each approach. The characteristics of the methods are discussed and compared.

Dexterous grasping of objects with uncertain pose is a hard unsolved problem in robotics. This paper solves this problem using information gain re-planning. First we show how tactile information, acquired during a failed attempt to grasp an object can be used to refine the estimate of that object's pose. Second, we show how this information can be used to replan new reach to grasp trajectories for successive grasp attempts. Finally we show how reach-to-grasp trajectories can be modified, so that they maximise the expected tactile information gain, while simultaneously delivering the hand to the grasp configuration that is most likely to succeed. Our main novel outcome is thus to enable tactile information gain planning for Dexterous, high degree of freedom (DoFs) manipulators. We achieve this using a combination of information gain planning, hierarchical probabilistic roadmap planning, and belief updating from tactile sensors for objects with non-Gaussian pose uncertainty in 6 dimensions. The method is demonstrated in trials with simulated robots. Sequential replanning is shown to achieve a greater success rate than single grasp attempts, and trajectories that maximise information gain require fewer re-planning iterations than conventional planning methods before a grasp is achieved.

We describe a method for learning planning operators for manipulation tasks from hand-written programs to provide a high-level command interface to a robot manipulator that allows tasks to be specified simply as goals. This is made challenging by the fact that a manipulator is a hybrid system-any model of it consists of discrete variables such as “holding cup” and continuous variables such as the poses of objects and position of the robot. The approach relies on three novel techniques: the action learning from annotated code uses simulation to find PDDL action models corresponding to code fragments. To provide the geometric information needed we use supervised learning to produce a mapping from geometric to symbolic state. The mapping can also be used in reverse to produce a geometric state that makes a set of predicates true, thus allowing desired object positions to be generated during planning. Finally, during execution of the plan we use a partially observable Markov decision problem-based planner to repair the initial plan when unforeseen geometric constraints prevent actions from being executed.

The mobile humanoid Rollin'Justin is a versatile experimental platform for research in manipulation tasks. Previously, different state of the art control methods and first autonomous task execution scenarios have been demonstrated. In this video two new applications with challenging task requirements are presented. One is the catching of one or even two flying balls using all of Justin's degrees of freedom. The other is the autonomous preparation of coffee. Both applications need adequate sensors to support local referencing. The required precision in position and timing is realized in software, using the sensor information, taking the varying precision of Justin's kinematic sub-chains into account and handling all timings in sub-millisecond range.

It contradicts the human's expectations when humanoid robots move awkwardly during manipulation tasks. The unnatural motion may be caused by awkward start or goal configurations or by probabilistic path planning processes that are often used. This paper shows that the choice of an arm's target configuration strongly effects planning time and how human-like a planned path appears. Human-like goal configurations are found using a criterion from ergonomics research. The knowledge which pose of the Tool Center Point (TCP) can be reached in a natural manner is encapsulated in a restricted reachability map for the robot arm.

In autonomous bimanual operation of a robot, parallelized planning and execution of a task is essential. Elements of a task have different functional and spatial relationships. They may depend on each other and have to be executed in a specific order or they may be independent and their order can be determined freely. Consequently, individual actions can be planned and executed in parallel or not. In a proof of concept, this paper shows that the structure of a task and its mapping onto subordinate planners can significantly influence planning speed and task execution. Independent tasks are planned using two parallel path planners. Dependent tasks are planned using one path planner for both arms. Using a simple, yet expandable experimentation scenario, the resulting recommendations for parameterizing path planners are verified on a humanoid robot. For execution on the real robot a violation of the rigid body model used in path planners had to be addressed.

Research on humanoid robots for use in servicing tasks, e.g. fetching and delivery, attracts steadily more interest. With “Rollin' Justin” a mobile robotic system and research platform is presented that allows sophisticated control algorithms and dexterous manipulation. This video gives an overview of the mobile humanoid robotic system “Rollin' Justin” with special emphasis on mechanical design features, control issues and high-level system capabilities such as human robot interaction.

Research on humanoid robots for use in servicing tasks, e.g. fetching and delivery, attracts steadily more interest. With Rollin' Justin a mobile robotic system and research platform is presented that allows the implementation and demonstration of sophisticated control algorithms and dexterous manipulation. Important problems of service robotics such as mobile manipulation and strategies for using the increased workspace and redundancy in manipulation task can be studied in detail. This paper gives an overview of the design considerations for a mobile platform and their realizations to transform the formerly table-mounted humanoid upper body system Justin into Rollin' Justin, a fully self-sustaining mobile research platform.

This video presents a telepresence system which enables a human operator to explore a remote environment by means of a multimodal man machine interface and rollin' JUSTIN as teleoperator. The man machine interface allows for bimanual, dexterous manipulation and, through two different operating modi of the man machine interface, wide area movement as well. A bimanual assembly task, consisting of grasping a connector, opening and closing it again, is shown in this video.