Peter Slaets

A demonstration tool with Kalman filter data processing for robot programming by human demonstration

This paper presents a modular demonstration tool for robot programming by human demonstration and an approach for the calibration of the tools sensors. The tool is equipped with a wrench sensor, twelve LED markers for fast and accurate six dimensional position tracking with the Krypton K600 camera system, a compact camera and a laser distance sensor. A gripper mechanism is mounted on the tool for grasping and manipulating objects. The design of the tool specifically focused on the demonstration of compliant motion task, with applications in manipulation and assembly tasks. The calibration approach first uses an extended Kalman Filter to convert the measured positions of three to twelve visible LEDs into the pose of the tool frame relative to the Krypton camera frame. Then, using a non minimal state Kalman filter, the force sensor calibration parameters are calculated, and the orientation of the Krypton camera frame relative to the world frame is defined. This calibration approach is verified in a real world experiment.

Construction of a geometric 3-D model from sensor measurements collected during compliant motion

This paper describes the construction of a geometric 3-D model from the identification of geometrical parameters (vertices and faces) of rigid polyhedral objects in the environment during the force-controlled execution of contact formation sequences. Following improvements with respect to the state of the art are made: (i) creation of a 3-D model from a previously unknown environment, (ii) the estimation of a force decomposition useful for feedback to a force controller or for monitoring the contact forces, (iii) a method to reduce the number of modelling parameters, leading to a computational reduction, a better precision and a more accurate geometric description.

An open embedded hardware and software architecture applied to industrial robot control

This paper presents an open embedded hardware and software architecture for industrial robot control. Open hardware refers to open source IP-core provided by the authors, while open software implies the use of open source software, specifically Linux and OROCOS [1]. Embedded implies integration of various functional blocks on one System-On-Chip board, for data acquisition, computation and control tasks, of relatively small size and low power consumption, compared to regular PC-based industrial controllers. The proposed architecture is a hardware and software co-design where an operating system running on an embedded processor drives the FPGA hardware controllers. It is industrial robot type independent, as long as the motors are equipped with incremental position encoders and driven by PWM signals. The architecture has been tested on an industrial Performer MK2 robot setup. Low cost, low power consumption, remarkable stability, high flexibility and expandability are the key advantages of the architecture for industrial robot control.

Incremental Building of a Polyhedral Feature Model for Programming by Human Demonstration of Force-Controlled Tasks

This paper describes the construction of a local polyhedral 3-D feature model derived from pose and wrench sensor measurements collected during a force-controlled execution of a sequence of polyhedral contact formations. The procedure consists of two steps: 1) the sensor measurements are filtered, resulting in a (nonminimal) representation of a 3-D feature model; and 2) identification of a reduced set of geometric parameters (vertices and faces) of the rigid polyhedral objects in the environment is performed. The following improvements with respect to the state of the art are made: 1) creation of a polyhedral 3-D feature model of a previously unknown polyhedral environment; 2) estimation of a force decomposition useful for feedback in a force controller or for monitoring the contact forces; and 3) reduction of the number of model parameters, leading to a computational reduction, a better precision of the geometric parameters, and a higher level description of the contact topology

Building Blocks for SLAM in Autonomous Compliant Motion

This paper presents our research group’s latest results in autonomous force-controlled manipulation tasks: (i) advanced non-linear estimators for simultaneous parameter estimation and contact formation “map building” for 6D contact tasks (with active sensing integrated into the task planner), and (ii) the application of these results to programming by human demonstration, for tasks involving contacts.

Multi RGB-D camera setup for generating large 3D point clouds

The advent of inexpensive RGB-D cameras brings new opportunities to capture a 3D environment. This paper presents a method to create a modular setup for generating a large 3D point cloud, with attention to the study of interference, the influence of a USB extension cable, and the calibration procedure. The study of interference includes the influence of the distance between the cameras, the orientation of the cameras, and the illumination. Furthermore, this paper proposes a number of evaluation metrics for similar setups.

An open embedded industrial robot hardware and software architecture applied to position control and visual servoing application

This paper presents an open embedded hardware and software architecture for industrial robot control applied to visual servoing system. This architecture is a hardware and software co-design where embedded processors drive the FPGA for motor control. It is robot type independent, as long as the motors are equipped with incremental position encoders and driven by PWM signals. Low cost, low power consumption, high stability, flexibility and expandability are the key advantages. The architecture and related IP cores are developed through a component-based design model which interprets a mechatronic system by computation, communication, configuration and coordination components, together with composition of these components and blackboxes. The motor controller IP core is provided in the consistency of open hardware. Open software implies the use of OROCOS (Bruyninckx, 2001). The performance of visual servoing behaviour is evaluated by visual coupling of a Performer MK2 robot and a KUKA lightweight robot.

Dynamic Gait Monitoring Mobile Platform.

Human gait is an important indicator of health. Existing gait analysis systems are either expensive, intrusive, or require structured environments such as a clinic or a laboratory. In this research, a low-cost, non-obtrusive, dynamic gait monitoring platform is presented. By utilizing a mobile robot equipped with a Kinect sensor, comprehensive gait information can be extracted. The mobile platform tracks the skeletal joint movements while following the person. The acquired skeletal joint data is filtered to improve detection. Gait parameters such as step length, cadence and gait cycle time are extracted by processing the filtered data. The proposed approach was validated by using a VICON motion capture system. Results show that the proposed system is able to accurately detect gait parameters but requires a calibration procedure. Even though the camera is moving while tracking, the performance is on par with existing works. Step times can be detected with an average accuracy of around 10 milliseconds. Step length can be detected with an average accuracy of a few

Modelling of Second Order Polynomial Surface Contacts for Programming by Human Demonstration

This paper presents a contribution to automatic model building in quadratic polynomial environments, in the context of programming by human demonstration. A human operator moves a demonstration tool equipped with a probe, in contact with an unknown environment. The motion of the demonstration tool is sensed with a 3D camera, and the interaction with the environment is sensed with a force/torque sensor. Both measurements are uncertain, and do not give direct information about the different objects in the environment (such as cylinders, spheres, planes,...) and their geometric parameters. This paper uses a Bayesian Sequential Monte Carlo method or particle filter, to recognize the different discrete objects that form the environment, and simultaneously estimate the continuous geometric parameters of these different quadratic polynomial objects. The result is a complete geometric model of an environment, with different quadratic polynomial objects at its building blocks. The approach has been verified using real world experimental data, in which it is able to recognize three different unknown quadratic polynomial objects, and estimate their geometric parameters.