Semi-autonomous exploration with robot teams in urban search and rescue

This paper presents the development of a semi-autonomous exploration approach for a rescue robot team exploring unknown urban search and rescue (USAR) environments. The approach consists of a direction-based exploration technique utilized by multiple robots to search an unknown cluttered environment. The technique uses an occupancy grid approach that uniquely considers: 1) the terrain information of an environment by classifying obstacle cells as climbable or non-climbable cells, as well as 2) the direction of approach of a robot into a cell in order to determine a robot's ability to traverse a cell of interest. A distance threshold technique is employed to determine when the robots in a team should share this information with each other to minimize exploration overlap. The performance of the direction-based semi-autonomous exploration approach was investigated and compared to autonomous exploration of the same robot teams in simulations conducted in USARSim. The results verified that there was a statistically significant increase in exploration coverage using the semi-autonomous exploration mode over the fully autonomous exploration mode. The simulations also verified the potential use of semi-autonomous exploration of a team with multiple rescue robots.

[1]  S. Balakirsky,et al.  Stable Navigation Solutions for Robots in Complex Environments , 2007, 2007 IEEE International Workshop on Safety, Security and Rescue Robotics.

[2]  Goldie Nejat,et al.  Learning based semi-autonomous control for robots in urban search and rescue , 2012, 2012 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR).

[3]  Songmin Jia,et al.  Research on map merging for multi-robotic system based on RTM , 2012, 2012 IEEE International Conference on Information and Automation.

[4]  Arnoud Visser,et al.  Towards heterogeneous robot teams for disaster mitigation: Results and performance metrics from RoboCup rescue , 2007, J. Field Robotics.

[5]  K. Ohno,et al.  Validation of Simulated Robots with Realistically Modeled Dimensions and Mass in USARSim , 2008, 2008 IEEE International Workshop on Safety, Security and Rescue Robotics.

[6]  Brian Yamauchi,et al.  Frontier-based exploration using multiple robots , 1998, AGENTS '98.

[7]  Lakmal D. Seneviratne,et al.  Evaluating USARSim for use in fire search and rescue , 2011, 2011 International Conference for Internet Technology and Secured Transactions.

[8]  Goldie Nejat,et al.  A hierarchical reinforcement learning based control architecture for semi-autonomous rescue robots in cluttered environments , 2010, 2010 IEEE International Conference on Automation Science and Engineering.

[9]  Sven Behnke,et al.  Evaluating the Efficiency of Frontier-based Exploration Strategies , 2010, ISR/ROBOTIK.

[10]  Salvatore Livatino,et al.  Reduced overlap frontier-based exploration with two cooperating mobile robots , 2010, 2010 IEEE International Symposium on Industrial Electronics.

[11]  Daniele Nardi,et al.  Semi-autonomous Coordinated Exploration in Rescue Scenarios , 2007, RoboCup.

[12]  Henrik I. Christensen,et al.  Coordination strategies for multi-robot exploration and mapping , 2014, Int. J. Robotics Res..

[13]  Robin R. Murphy,et al.  Human-robot interactions during the robot-assisted urban search and rescue response at the World Trade Center , 2003, IEEE Trans. Syst. Man Cybern. Part B.

[14]  Maarten van Zomeren.  Search Methods in USAR , 2008 .

[15]  Dan R. Olsen,et al.  Fan-out: measuring human control of multiple robots , 2004, CHI.

[16]  Prasanna Velagapudi,et al.  Towards an understanding of the impact of autonomous path planning on victim search in USAR , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.