Jesse Clark is a software engineer who has built distributed systems for a number of Silicon Valley startups. At NASA he developed databases for the International Space Station and robotic simulations for the Hubble Space Telescope.
Gudi, S.L.K.C., ojha, S., clark, J., johnston, B. & williams, M.-.A. 2017, 'Fog Robotics: An Introduction', IEEE/RSJ International Conference on Intelligent Robots and Systems.View/Download from: UTS OPUS
Cloud Robotics (CR) is an emerging and
successful approach to robotics. The number of robots or other
IoT devices may increase drastically in the future which might
need higher bandwidth and there might be security concerns. If
robots in CR are not secured then robots can even become
surveillance bot by hackers. Moreover, if an internet
connection is lost due to network hitches then in that crucial
moment robot may not be available to complete its given task.
Consider a robot helping in disaster relief task then it might
stop working unexpectedly or work with the instructions from
hacker. In order to address such problems, we propose a new
approach to robotics - 'Fog Robotics (FR) in this paper, so a
network of robots can be used more securely and efficiently as
compared to CR.
Raza, S.A., Clark, J. & Williams, M. 2016, 'On Designing Socially Acceptable Reward Shaping', Social Robotics, International Conference on Social Robotics (ICSR), Springer, Kansas City, MO, USA, pp. 860-869.View/Download from: UTS OPUS or Publisher's site
For social robots, learning from an ordinary user should be socially appealing. Unfortunately, machine learning demands an enormous amount of human data, and a prolonged interactive teaching session becomes anti-social. We have addressed this problem in the context of reward shaping for reinforcement learning. For efficient reward shaping, a continuous stream of rewards is expected from the teacher. We present a simple framework which seeks rewards for a small number of steps from each of a large number of human teachers. Therefore, it simplifies the job of an individual teacher. The framework was tested with online crowd workers on a transport puzzle. We thoroughly analyzed the quality of the learned policies and crowd's teaching behavior. Our results showed that nearly perfect policies can be learned using this framework. The framework was generally acceptable in the crowd's opinion.