Daniel Claes

Collision avoidance under bounded localization uncertainty

We present a multi-mobile robot collision avoidance system based on the velocity obstacle paradigm. Current positions and velocities of surrounding robots are translated to an efficient geometric representation to determine safe motions. Each robot uses on-board localization and local communication to build the velocity obstacle representation of its surroundings. Our close and error-bounded convex approximation of the localization density distribution results in collision-free paths under uncertainty. While in many algorithms the robots are approximated by circumscribed radii, we use the convex hull to minimize the overestimation in the footprint. Results show that our approach allows for safe navigation even in densely packed environments.

OctoSLAM: A 3D mapping approach to situational awareness of unmanned aerial vehicles

The focus of this paper is on situational awareness of airborne agents capable of 6D motion, in particular multi-rotor UAVs. We propose the fusion of 2D laser range finder, altitude, and attitude sensor data in order to perform simultaneous localization and mapping (SLAM) indoors. In contrast to other planar 2D laser range finder based SLAM approaches, we perform SLAM on a 3D instead of a 2D map. To represent the 3D environment an octree based map is used. Our scan registration algorithm is derived from Hector SLAM. We evaluate the performance of our system in simulation and on a real multirotor UAV equipped with a 2D laser range finder, inertial measurement unit, and altitude sensor. The results show significant improvement in the localization and representation accuracy over current 2D map SLAM methods. The system is implemented using Willow Garages robot operating system.

How to Win RoboCup@Work?

In this paper we summarize how the Swarmlab@Work team has won the 2013 world championship title in the RoboCup@Work league, which aims to facilitate the use of autonomous robots in industry. The various techniques that have been combined to win the competition come from different computer science domains, entailing learning, (simultaneous) localization and mapping, navigation, object recognition and object manipulation. While the RoboCup@Work league is not a standard platform league, all participants used a (customized) Kuka youBot. The youBot is a ground based platform, capable of omnidirectional movement and equipped with a five degree of freedom arm featuring a parallel gripper.

Multi robot collision avoidance in a shared workspace

This paper presents a decentralised human-aware navigation algorithm for shared human–robot work-spaces based on the velocity obstacles paradigm. By extending our previous work on collision avoidance, we are able to include and avoid static and dynamic obstacles, no matter whether they are induced by other robots and humans passing through. Using various cost maps and Monte Carlo sampling with different cost factors accounting for humans and robots, the approach allows human workers to use the same navigation space as robots. It does not rely on any external positioning sensors and shows its feasibility even in densely packed environments.

Human Robot-Team Interaction

In this paper we present a human robot-team interaction solution for automated task handling in an industrial work environment. The main idea is that multiple heterogenous robots with different capabilities support human workers by autonomously performing tasks for them. When a human worker asks for a specific item the robots need to collaborate as a team to grasp the item and bring it to the user. The approach combines various techniques from vision, robotics and multi-agent systems to create a flexible, low-cost solution for different task allocation problems. A proof of concept is implemented on a mobile manipulation platform and a low-cost personal robot.

Bio-inspired multi-robot systems

Abstract In this chapter, we discuss team coordination in multi-robot systems inspired by the behavior of social insets such as ants and honeybees. Specifically, we study the application instances of ant-inspired robot coverage and bee-inspired robot foraging and pheromone signaling mechanisms and introduce some of our bio-inspired algorithms to deal with these problems. By robot coverage, we refer to the problem of deploying a robotic swarm in the environment with the task of maximizing the sensor coverage of the environment, and by robot foraging we refer to the problem of exploring the environment in search of food or provisions.

Winning the RoboCup@Work 2014 Competition: The smARTLab Approach

In this paper we summarise the approach of the smARTLab@Work team that has won the 2014 RoboCup@Work competition. smARTLab (swarms, multi-agent, and robot technologies and learning lab) is a robotics research lab that is part of the Agent ART group at the computer science department of the University of Liverpool. This team has won the competition for the second year in a row. The team previously competed as swarmlab@Work and changed name after the move of professor Tuyls and his research group from Maastricht University to the University of Liverpool, UK. The various techniques that have been combined to win the competition come from different computer science domains, including machine learning, (simultaneous) localisation and mapping, navigation, object recognition and object manipulation. While the RoboCup@Work league is not a standard platform league, all participants use a (customised) KUKA youBot. The stock youBot is a ground based platform, capable of omnidirectional movement and equipped with a five degree of freedom arm featuring a parallel gripper. We present our adaptations to the robot, in which the replacement of the gripper was the most important upgrade comparing to the version of the robot that was used last year.

Development of an Autonomous RC-car

In this paper we tackle the development of a robotic-car with hardware control, lane detection, mapping, localization and path planning capabilities. We aim for a completely independent, reliable and robust system that can traverse a single lane track bordered by white lines on an optimal path. To detect the track boundaries, we implement two different approaches. A RANSAC approach, which approximates the lines by random sampling of splines, and a polyline approach, which applies primitive image processing in combination with a road model. To map the environment, odometry and vision-based information is fused by a particle filter based Simultaneous Localization and Mapping system. The map is afterwards used in conjunction with Adaptive Monte Carlo Localization. For path planning, a one step continuous-curvature approach based on sensor or maps data is used. To offer more detailed information about the environment, we introduce a generic map analysis system. It is employed to evaluate the efficiency of certain paths on the track.