Michael Gienger

Task-oriented whole body motion for humanoid robots

We present a whole body motion control algorithm for humanoid robots. It is based on the framework of Liegeois and solves the redundant inverse kinematics problem on velocity level. We control the hand positions as well as the hand and head attitude. The attitude is described with a novel 2-dof description suited for symmetrical problems. Task-specific command elements can be assigned to the command vector at any time, such enabling the system to control one or multiple effectors and to seamlessly switch between such modes while generating a smooth, natural motion. Further, kinematic constraints can be assigned to individual degrees of freedom. The underlying kinematic model does not consider the leg joints explicitly. Nevertheless, the method can be used in combination with an independent balance or walking control system, such reducing the complexity of a complete system control. We show how to incorporate walking in this control scheme and present experimental results on ASIMO

Towards the design of a biped jogging robot

Deals with the design and control of an anthropomorphic autonomous biped robot. The objective is to realize a dynamically stable, three-dimensional walking and jogging motion. The design, sensors and electronics of the robot are introduced. Particular emphasis has been devoted to achieving a high power-to-weight ratio. The corresponding methods for weight reduction are presented. The control scheme is discussed. It is based on the method of feedback linearization employing the equations of motion of the system.

Goal Babbling Permits Direct Learning of Inverse Kinematics

We present an approach to learn inverse kinematics of redundant systems without prior- or expert-knowledge. The method allows for an iterative bootstrapping and refinement of the inverse kinematics estimate. The essential novelty lies in a path-based sampling approach: we generate training data along paths, which result from execution of the currently learned estimate along a desired path towards a goal. The information structure thereby induced enables an efficient detection and resolution of inconsistent samples solely from directly observable data. We derive and illustrate the exploration and learning process with a low-dimensional kinematic example that provides direct insight into the bootstrapping process. We further show that the method scales for high dimensional problems, such as the Honda humanoid robot or hyperredundant planar arms with up to 50 degrees of freedom.

The concept of jogging JOHNNIE

Within the large variety of existing and still newly emerging biped walking machines Jogging JOHNNIE represents a fundamental study on fast walking and on especially adapted foot-dynamics. Air phases are possible with two feet lifted off the ground. Each foot possesses six degrees of freedom with respect to the body and additionally seven degrees of freedom within the local foot environment. The overall system includes 23 degrees of freedom. It is 1.80 m, large and weighs 40 kg. Up to now stable walking has been achieved.

Gaussian process implicit surfaces for shape estimation and grasping

The choice of an adequate object shape representation is critical for efficient grasping and robot manipulation. A good representation has to account for two requirements: it should allow uncertain sensory fusion in a probabilistic way and it should serve as a basis for efficient grasp and motion generation. We consider Gaussian process implicit surface potentials as object shape representations. Sensory observations condition the Gaussian process such that its posterior mean defines an implicit surface which becomes an estimate of the object shape. Uncertain visual, haptic and laser data can equally be fused in the same Gaussian process shape estimate. The resulting implicit surface potential can then be used directly as a basis for a reach and grasp controller, serving as an attractor for the grasp end-effectors and steering the orientation of contact points. Our proposed controller results in a smooth reach and grasp trajectory without strict separation of phases. We validate the shape estimation using Gaussian processes in a simulation on randomly sampled shapes and the grasp controller on a real robot with 7DoF arm and 7DoF hand.

Sensors and Control Concept of Walking “Johnnie”

One key problem to achieve a dynamically stable walking motion with biped robots is to measure and control the actual state of the robot with respect to its environment. Dynamically stable walking on unstructured terrain and fast walking can only be achieved with an orientation sensor. The control system of the biped robot “Johnnie” is designed such that the orientation of the upper body is controlled throughout all phases of the gait pattern. Furthermore, a sophisticated measurement and control of the foot torques has been implemented. In this way, the interaction forces and torques between robot and environment are controlled and tilting of the foot is avoided.

Whole body humanoid control from human motion descriptors

Many advanced motion control strategies developed in robotics use captured human motion data as valuable source of examples to simplify the process of programming or learning complex robot motions. Direct and online control of robots from observed human motion has several inherent challenges. The most important may be the representation of the large number of mechanical degrees of freedom involved in the execution of movement tasks. Attempting to map all such degrees of freedom from a human to a humanoid is a formidable task from an instrumentation and sensing point of view. More importantly, such an approach is incompatible with mechanisms in the central nervous system which are believed to organize or simplify the control of these degrees of freedom during motion execution and motor learning phase. Rather than specifying the desired motion of every degree of freedom for the purpose of motion control, it is important to describe motion by low dimensional motion primitives that are defined in Cartesian (or task) space. In this paper, we formulate the human to humanoid retargeting problem as a task space control problem. The control objective is to track desired task descriptors while satisfying constraints such as joint limits, velocity limits, collision avoidance, and balance. The retargeting algorithm generates the joint space trajectories that are commanded to the robot. We present experimental and simulation results of the retargeting control algorithm on the Honda humanoid robot ASIMO.

Task-level imitation learning using variance-based movement optimization

Recent advances in the field of humanoid robotics increase the complexity of the tasks that such robots can perform. This makes it increasingly difficult and inconvenient to program these tasks manually. Furthermore, humanoid robots, in contrast to industrial robots, should in the distant future behave within a social environment. Therefore, it must be possible to extend the robots abilities in an easy and natural way. To address these requirements, this work investigates the topic of imitation learning of motor skills. The focus lies on providing a humanoid robot with the ability to learn new bi-manual tasks through the observation of object trajectories. For this, an imitation learning framework is presented, which allows the robot to learn the important elements of an observed movement task by application of probabilistic encoding with Gaussian Mixture Models. The learned information is used to initialize an attractor-based movement generation algorithm that optimizes the reproduced movement towards the fulfillment of additional criteria, such as collision avoidance. Experiments performed with the humanoid robot ASIMO show that the proposed system is suitable for transferring information from a human demonstrator to the robot. These results provide a good starting point for more complex and interactive learning tasks.

ONLINE TRANSFER OF HUMAN MOTION TO HUMANOIDS

Transferring motion from a human demonstrator to a humanoid robot is an important step toward developing robots that are easily programmable and that can replicate or learn from observed human motion. The so called motion retargeting problem has been well studied and several off-line solutions exist based on optimization approaches that rely on pre-recorded human motion data collected from a marker-based motion capture system. From the perspective of human robot interaction, there is a growing interest in online motion transfer, particularly without using markers. Such requirements have placed stringent demands on retargeting algorithms and limited the potential use of off-line and pre-recorded methods. To address these limitations, we present an online task space control theoretic retargeting formulation to generate robot joint motions that adhere to the robots joint limit constraints, joint velocity constraints and self-collision constraints. The inputs to the proposed method include low dimensional normalized human motion descriptors, detected and tracked using a vision based key-point detection and tracking algorithm. The proposed vision algorithm does not rely on markers placed on anatomical landmarks, nor does it require special instrumentation or calibration. The current implementation requires a depth image sequence, which is collected from a single time of flight imaging device. The feasibility of the proposed approach is shown by means of online experimental results on the Honda humanoid robot — ASIMO.

Optimization of sequential attractor-based movement for compact behaviour generation

In this paper, we propose a novel method to generate optimal robot motion based on a sequence of attractor dynamics in task space. This is motivated by the biological evidence that movements in the motor cortex of animals are encoded in a similar fashion- and by the need for compact movement representations on which efficient optimization can be performed. We represent the motion as a sequence of attractor points acting in the task space of the motion. Based on this compact and robust representation, we present a scheme to generate optimal movements. Unlike traditional optimization techniques, this optimization is performed on the low-dimensional representation of the attractor points and includes the underlying control loop itself as subject to optimization. We incorporate optimality criteria such as e.g. the smoothness of the motion, collision distance measures, or joint limit avoidance. The optimization problem is solved efficiently employing the analytic equations of the overall system. Due to the fast convergence, the method is suited for dynamic environments, including the interaction with humans. We will present the details of the optimization scheme, and give a description of the chosen optimization criteria. Simulation and experimental results on the humanoid robot ASIMO will underline the potential of the proposed approach.