Zhixing Xue

The KIT object models database: An object model database for object recognition, localization and manipulation in service robotics

For the execution of object recognition, localization and manipulation tasks, most algorithms use object models. Most models are derived from, or consist of two-dimensional (2D) images and/or three-dimensional (3D) geometric data. The system described in this article was constructed specifically for the generation of such model data. It allows 2D image and 3D geometric data of everyday objects be obtained semi-automatically. The calibration provided allows 2D data to be related to 3D data. Through the use of high-quality sensors, high-accuracy data is achieved. So far over 100 objects have been digitized using this system and the data has been successfully used in several international research projects. All of the models are freely available on the web via a front-end that allows preview and filtering of the data.

Automatic optimal grasp planning based on found contact points

Automatic grasp planning systems are very important for service robots, which compute what forces should be exerted onto the object and how those forces can be applied by robotic hands. In this paper, a highly integrated grasp planning system is introduced. Initial grasp is computed in the grasp simulator GraspIt! combining hand preshapes and automatically generated approach directions. With fixed relative position and orientation between the robotic hand and object as by the initial grasp, all the contact points between the fingers and the object are efficiently found. A search process tries to improve the grasp quality by moving the fingers to its neighbored joint positions, and uses the corresponding contact points to the joint position to evaluate the grasp quality, until local maximum grasp quality is reached. Optimal forces for the found grasp is computed as a linear inequalities matrix problem, which are exerted onto the object using torque based finger impedance control during execution. Experiments on Schunk Anthropomorphic Hand with 13 degrees of freedom show that, using the introduced grasp planning system, the object can be grasped solidly with shift errors of only some millimeters.

Grasp planning: Find the contact points

Automatically grasp planning for dexterous hand with a large number of degrees of freedom (DOF) is still a challenging problem. Two groups of grasp quality measurements can be considered: one associated with the position of contact points and the other associated with the hand configuration. In this paper, we propose a novel approach to bridge the gap between the two grasp quality measurements by finding all possible contact points between a robotic hand and an object with given position and orientation. This way the contact points fulfill the second group of measurements. The first group of measurements can be used to find the best grasp, which could be executed on a real hand without unreachable or joint limit problems. We use a continuous collision detection algorithm and swept volume to efficiently gather all possible contact points through the entire configuration space of each finger. Results of finding contact points between the Schunk Anthromorph Hand (SAHand) with 13 DOFs and various objects in every- days environment are presented.

Integration of 6D Object Localization and Obstacle Detection for Collision Free Robotic Manipulation

The major goal of research regarding mobile service robotics is to enable a robot to assist human beings in their everyday life. This implies that the robot will have to deal with everyday life environments. One of the most important steps towards able service robots is to enhance the ability to operate well in unstructured living environments. In this paper we focus on the integration of object recognition, obstacle detection and collision free manipulation to increase the service robots manipulation abilities in the context of highly unstructured environments.

Planning regrasp operations for a multifingered robotic hand

Regrasp operations consist of a sequence of pick-and-place operations, which are very useful to avoid collisions with the environment and to overcome the kinematic limitations in some cases. In this work, we propose an automatic planning system for regrasp operations for a multifingered robotic hand. The stable planes of the object to be grasped are automatically found. The minimal angle allowed to rotate the object without tipping it over is expressed using solid angles to quantify the stability of each stable plane. The grasp for the multifingered hand is generated in the simulation using hand preshapes and approach directions. The stable planes are placed in the simulation as obstacles to plan grasps that do not collide with such stable planes. After a grasp is found, collisions between the grasp and each stable plane are checked. This information and the found grasps computed off-line are saved in a grasp database. During on-line execution, regrasp operations are planned by a breadth-first search using the grasp database. The collision and kinematic feasibility are also considered by the planner.

Dexterous manipulation planning of objects with surface of revolution

In this paper, we propose a novel method for dexterous manipulation planning problem of rotating object with surface of revolution using a robotic multi-fingered hand. This method finds contact point trajectories from contact points between the robotic hand and the object with task-orientated manipulation quality measurement. Based on the defined manipulation quality, the pose for robotic hand relative to object can also be optimized by random sample. Experiments using Schunk anthropomorphic hand with 13 degrees of freedom screwing a light bulb into holder with screw thread demonstrates the feasibility and efficiency of the introduced method.

Learning of probabilistic grasping strategies using Programming by Demonstration

The planning of grasping motions is demanding due to the complexity of modern robot systems. In Programming by Demonstration, the observation of a human teacher allows to draw additional information about grasping strategies. Rosell showed, that the motion planning problem can be simplified by globally restricting the set of valid configurations to a learned subspace. In this work, the transformation of a humanoid grasping strategy to an anthropomorphic robot system is described by a probabilistic model, called variation model, in order to account for modeling and transformation errors. The variation model resembles a soft preference for grasping motions similar to the demonstration and therefore induces a non-uniform sampling distribution on the configuration space. The sampling distribution is used in a standard probabilistic motion planner to plan grasping motions efficiently for new objects in new environments.

Learning of Planning Models for Dexterous Manipulation Based on Human Demonstrations

In the human environment service robots have to be able to manipulate autonomously a large variety of objects in a workspace restricted by collisions with obstacles, self-collisions and task constraints. Planning enables the robot system to generalize predefined or learned manipulation knowledge to new environments. For dexterous manipulation tasks the manual definition of planning models is time-consuming and error-prone. In this work, planning models for dexterous tasks are learned based on multiple human demonstrations using a general feature space including automatically generated contact constraints, which are automatically relaxed to consider the correspondence problem. In order to execute the learned planning model with different objects, the contact location is transformed to given object geometry using morphing. The initial, overspecialized planning model is generalized using a previously described, parallelized optimization algorithm with the goal to find a maximal subset of task constraints, which admits a solution to a set of test problems. Experiments on two different, dexterous tasks show the applicability of the learning approach to dexterous manipulation tasks.

Towards automatic manipulation action planning for service robots

A service robot should be able to automatically plan manipulation actions to help people in domestic environments. Following the classic senseplan-act cycle, in this paper we present a planning system based on a symbolic planner, which can plan feasible manipulation actions and execute it on a service robot. The approach consists of five steps. Scene Mapping formulates object relations from the current scene for the symbolic planner. Discretization generates discretized symbols for Planning. The planned manipulation actions are checked by Verification, so that it is guaranteed that they can be performed by the robot during Execution. Experiments of planned pick-and-place and pour-in tasks on real robot show the feasibility of our method.

Autonomous grasp and manipulation planning using a ToF camera

A time-of-flight camera can help a service robot to sense its 3D environment. In this paper, we introduce our methods for sensor calibration and 3D data segmentation to use it to automatically plan grasps and manipulation actions for a service robot. Impedance control is intensively used to further compensate the modeling error and to apply the computed forces. The methods are further demonstrated in three service robotic applications. Sensor-based motion planning allows the robot to move within dynamic and cluttered environment without collision. Unknown objects can be detected and grasped. In the autonomous ice cream serving scenario, the robot captures the surface of ice cream and plans a manipulation trajectory to scoop a portion of ice cream.