Follow me robot using bluetooth-based position estimation

Human-Following robots are being actively researched for their immense potential to carry out mundane tasks like load carrying and monitoring of target individual through interaction and collaboration. The recent advancements in vision and sensor technologies have helped in creating more user-friendly robots that are able to coexist with humans by leveraging the sensors for human detection, human movement estimation, collision avoidance, and obstacle avoidance. But most of these sensors are suitable only for Line of Sight following of human. In the case of loss of sight of the target, most of them fail to re-acquire their target. In this paper, we are proposing a novel method to develop a human following robot using Bluetooth and Inertial Measurement Unit (IMU) on Smartphones which can work under high interference environment and can reacquire the target when lost. The proposed method leverages IMU sensors on the smartphone to estimate the direction of human movement while estimating the distance traveled from the RSSI of the Bluetooth. Thus, the Follow Me robot which estimates the position of target human and direction of heading and effectively track the person was implemented using Smartphone on a differential drive robot.

[1]  Michele Caldara,et al.  Indoor distance estimated from Bluetooth Low Energy signal strength: Comparison of regression models , 2016, 2016 IEEE Sensors Applications Symposium (SAS).

[2]  Horst-Michael Gross,et al.  Sensor Fusion for Vision and Sonar Based People Tracking on a Mobile Service Robot , 2002 .

[3]  Hiroshi Mizoguchi,et al.  Recovery function for human following robot losing target , 2013, IECON 2013 - 39th Annual Conference of the IEEE Industrial Electronics Society.

[4]  Jian Huang,et al.  Advanced service robotics for human assistance and support , 2011, 2011 International Conference on Advanced Computer Science and Information Systems.

[5]  Martin Nilsson,et al.  Indoor positioning using multi-frequency RSS with foot-mounted INS , 2014, 2014 International Conference on Indoor Positioning and Indoor Navigation (IPIN).

[6]  Frederic T. Chong,et al.  Smartphone Evolution and Reuse: Establishing a More Sustainable Model , 2010, 2010 39th International Conference on Parallel Processing Workshops.

[7]  Xose Manuel Pardo,et al.  Feature analysis for human recognition and discrimination: Application to a person-following behaviour in a mobile robot , 2012, Robotics Auton. Syst..

[8]  Aaron Striegel,et al.  Accurate Extraction of Face-to-Face Proximity Using Smartphones and Bluetooth , 2011, 2011 Proceedings of 20th International Conference on Computer Communications and Networks (ICCCN).

[9]  Christian Schlegel,et al.  Vision Based Person Tracking with a Mobile Robot , 1998, BMVC.

[10]  Hiroshi Matsuo,et al.  Experiments of position estimation by BLE beacons on actual situations , 2015, 2015 IEEE 4th Global Conference on Consumer Electronics (GCCE).

[11]  M. M. Rahman,et al.  A multi-step approach for RSSi-based distance estimation using smartphones , 2015, 2015 International Conference on Networking Systems and Security (NSysS).

[12]  Salman Afghani,et al.  FOLLOW ME ROBOT USING INFRARED BEACONS , 2013 .

[13]  Martin Fischer,et al.  Service Robotics and Human Labor: A first technology assessment of substitution and cooperation , 2017, Robotics Auton. Syst..

[14]  Hiroshi Matsuo,et al.  Experiment of indoor position presumption based on RSSI of Bluetooth LE beacon , 2014, 2014 IEEE 3rd Global Conference on Consumer Electronics (GCCE).

[15]  Ning An,et al.  Human recognition for following robots with a Kinect sensor , 2016, 2016 IEEE International Conference on Robotics and Biomimetics (ROBIO).