Online planning for multi-robot active perception with self-organising maps

Graeme Best; Jan Faigl; Robert Fitch

doi:10.1007/s10514-017-9691-4

Online planning for human–multi-robot interactive theatrical performance

Autonomous Robots ◽

10.1007/s10514-018-9755-0 ◽

2018 ◽

Vol 42 (8) ◽

pp. 1771-1786 ◽

Cited By ~ 4

Author(s):

Ellen A. Cappo ◽

Arjav Desai ◽

Matthew Collins ◽

Nathan Michael

Keyword(s):

Online Planning ◽

Theatrical Performance ◽

Multi Robot

Download Full-text

A Novel Double Layered Hybrid Multi-Robot Framework for Guidance and Navigation of Unmanned Surface Vehicles in a Practical Maritime Environment

Journal of Marine Science and Engineering ◽

10.3390/jmse8090624 ◽

2020 ◽

Vol 8 (9) ◽

pp. 624 ◽

Cited By ~ 2

Author(s):

Yogang Singh ◽

Marco Bibuli ◽

Enrica Zereik ◽

Sanjay Sharma ◽

Asiya Khan ◽

...

Keyword(s):

Motion Planning ◽

Formation Control ◽

Optimal Path ◽

Unmanned Surface Vehicles ◽

Research Areas ◽

Online Planning ◽

Cooperative Motion ◽

Aggregation Technique ◽

Global And Local ◽

Multi Robot

Formation control and cooperative motion planning are two major research areas currently being used in multi robot motion planning and coordination. The current study proposes a hybrid framework for guidance and navigation of swarm of unmanned surface vehicles (USVs) by combining the key characteristics of formation control and cooperative motion planning. In this framework, two layers of offline planning and online planning are integrated and applied on a practical marine environment. In offline planning, an optimal path is generated from a constrained A* path planning approach, which is later smoothed using a spline. This optimal trajectory is fed as an input for the online planning where virtual target (VT) based multi-agent guidance framework is used to navigate the swarm of USVs. This VT approach combined with a potential theory based swarm aggregation technique provides a robust methodology of global and local collision avoidance based on known positions of the USVs. The combined approach is evaluated with the different number of USVs to understand the effectiveness of the approach from the perspective of practicality, safety and robustness.

Download Full-text

Dec-MCTS: Decentralized planning for multi-robot active perception

The International Journal of Robotics Research ◽

10.1177/0278364918755924 ◽

2018 ◽

Vol 38 (2-3) ◽

pp. 316-337 ◽

Cited By ~ 17

Author(s):

Graeme Best ◽

Oliver M Cliff ◽

Timothy Patten ◽

Ramgopal R Mettu ◽

Robert Fitch

Keyword(s):

Convergence Rates ◽

Real Data ◽

Optimization Approach ◽

Active Perception ◽

Active Object ◽

Monte Carlo Tree Search ◽

Tree Expansion ◽

Team Orienteering ◽

Active Object Recognition ◽

Multi Robot

We propose a decentralized variant of Monte Carlo tree search (MCTS) that is suitable for a variety of tasks in multi-robot active perception. Our algorithm allows each robot to optimize its own actions by maintaining a probability distribution over plans in the joint-action space. Robots periodically communicate a compressed form of their search trees, which are used to update the joint distribution using a distributed optimization approach inspired by variational methods. Our method admits any objective function defined over robot action sequences, assumes intermittent communication, is anytime, and is suitable for online replanning. Our algorithm features a new MCTS tree expansion policy that is designed for our planning scenario. We extend the theoretical analysis of standard MCTS to provide guarantees for convergence rates to the optimal payoff sequence. We evaluate the performance of our method for generalized team orienteering and online active object recognition using real data, and show that it compares favorably to centralized MCTS even with severely degraded communication. These examples demonstrate the suitability of our algorithm for real-world active perception with multiple robots.

Download Full-text

Multi-robot path planning for budgeted active perception with self-organising maps

2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) ◽

10.1109/iros.2016.7759489 ◽

2016 ◽

Cited By ~ 13

Author(s):

Graeme Best ◽

Jan Faigl ◽

Robert Fitch

Keyword(s):

Path Planning ◽

Robot Path Planning ◽

Active Perception ◽

Robot Path ◽

Multi Robot

Download Full-text

Distributed Decision-Theoretic Active Perception for Multi-robot Active Information Gathering

Modeling Decisions for Artificial Intelligence - Lecture Notes in Computer Science ◽

10.1007/978-3-319-12054-6_6 ◽

2014 ◽

pp. 60-71 ◽

Cited By ~ 2

Author(s):

Jennifer Renoux ◽

Abdel-Illah Mouaddib ◽

Simon LeGloannec

Keyword(s):

Information Gathering ◽

Active Perception ◽

Distributed Decision ◽

Multi Robot ◽

Active Information Gathering

Download Full-text

Scan Matching Based Multi-robot Map Building

International Academy of Engineers Feb. 8-9, 2015 Kuala Lumpur (Malaysia) ◽

10.15242/iae.iae0215221 ◽

2015 ◽

Keyword(s):

Map Building ◽

Scan Matching ◽

Multi Robot

Download Full-text

Tire Rolling Kinematics Model for an Intelligent Tire Based on an Accelerometer

Tire Science and Technology ◽

10.2346/tire.20.190211 ◽

2020 ◽

Vol 48 (4) ◽

pp. 287-314

Author(s):

Yan Wang ◽

Zhe Liu ◽

Michael Kaliske ◽

Yintao Wei

Keyword(s):

Elastic Deformation ◽

Estimation Algorithm ◽

Force Sensor ◽

Euler Method ◽

Rolling Contact ◽

Body Motion ◽

Identification Algorithm ◽

Active Perception ◽

Kinematics Model ◽

Ring Model

ABSTRACT The idea of intelligent tires is to develop a tire into an active perception component or a force sensor with an embedded microsensor, such as an accelerometer. A tire rolling kinematics model is necessary to link the acceleration measured with the tire body elastic deformation, based on which the tire forces can be identified. Although intelligent tires have attracted wide interest in recent years, a theoretical model for the rolling kinematics of acceleration fields is still lacking. Therefore, this paper focuses on an explicit formulation for the tire rolling kinematics of acceleration, thereby providing a foundation for the force identification algorithms for an accelerometer-based intelligent tire. The Lagrange–Euler method is used to describe the acceleration field and contact deformation of rolling contact structures. Then, the three-axis acceleration vectors can be expressed by coupling rigid body motion and elastic deformation. To obtain an analytical expression of the full tire deformation, a three-dimensional tire ring model is solved with the tire–road deformation as boundary conditions. After parameterizing the ring model for a radial tire, the developed method is applied and validated by comparing the calculated three-axis accelerations with those measured by the accelerometer. Based on the features of acceleration, especially the distinct peak values corresponding to the tire leading and trailing edges, an intelligent tire identification algorithm is established to predict the tire–road contact length and tire vertical load. A simulation and experiments are conducted to verify the accuracy of the estimation algorithm, the results of which demonstrate good agreement. The proposed model provides a solid theoretical foundation for an acceleration-based intelligent tire.

Download Full-text