The first week of the UW Stout Robotics REU has flown by. Monday was spent unpacking and getting settled in, and Tuesday we toured the campus and the Stout Vocational Rehabilitation Institute. The rest of the week was spent working with my team, Robert and Haiming. The UW Stout campus is beautiful, along with Menomonie. I have gone on a few bike rides in the area and enjoyed it immensely.
The highlight has been getting to know the robot we will be working with, the Kinova JACO2. We have been practicing controlling JACO and reading about previous research done with JACO and other assistive robot arms.
JACO is a robotic arm that can be attached to a user’s motorized wheelchair. Benefits of the JACO robot are both physical and economic, as it has been shown that increased independence of users can decrease caregiver time by 42% . This robot is controlled by a joystick, through which a user can switch to different modes for translation, movement of the wrist, and opening and closing the fingers. Controlling the JACO arm can be cumbersome in this way, as switching modes for different movements is not intuitive or time efficient . Several attempts have been made in an attempt to alleviate this difficulty, such as the development of “time-optimal mode switching” software for simple tasks or using “Brain-Computer interfaces” to control the robot’s fingers -. The goal is to increase usability through the creation of a meal assistance feature. Through the use of a camera, the Kinova JACO, and MATLAB software, facial detection will be used to deliver food to a user’s mouth when they open their mouth. There has been a number of studies already in which meal assistance robots have been created. Tanaka et al. developed a robotic system that would grab a cup and bring it to the user’s face. Through the use of a “facial recognition function” the robot was able to reliably bring the cup to the user’s face. Bhalla et al. used a JACO arm to improve a “semi-autonomous wheelchair” in an effort to create a robot for those with Locked-In syndrome. They mounted an ASUS XTION PRO Live to the back of the wheelchair to communicate locations of obstacles to the JACO arm. In this way, they were successfully able to grasps objects such as apples and oranges and bring them to a user’s mouth. Kuriyama et al. created a model for spillage using a “CFD simulator”, which predicted the movement of the liquid in a spoon due to the track of a robot arm. The REU study will differ as the objective is to signal when the user wants to eat, and then the robot will bring the food to the user’s face with a pre-programmed trajectory. This work could have great impact for existing users of JACO as it will make eating a much simpler activity and more efficient activity .
 V. Maheu, J. Frappier, P. Archambault and F. Routhier, “Evaluation of the JACO robotic arm: Clinico-economic study for powered wheelchair users with upper-extremity disabilities”, 2011 IEEE International Conference on Rehabilitation Robotics, 2011.
L. Herlant, R. Holladay and S. Srinivasa, “Assistive Teleoperation of Robot Arms via Automatic Time-Optimal Mode Switching”, in The Eleventh ACM/IEEE International Conference on Human Robot Interaction, Christchurch, 2016, pp. 35-42.
 L. Bougrain, “BCI-based control of a JACO robotic arm with OpenVIBE”, Graz, 2014.
 H. Tanaka, Y. Sumi and Y. Matsumoto, “Assistive robotic arm autonomously bringing a cup to the mouth by face recognition”, 2010 IEEE Workshop on Advanced Robotics and its Social Impacts, pp. 34-39, 2010.
 T. Bhalla, D. Fox, R. Nayeem, T. Rhodes and M. Warner, “Design and Validation for Control Interfaces for Anna”, Worcester Polytechnic Institute, pp. 14-26, 2015.
 Y. Kuriyama, K. Yano and M. Hamaguchi, “Trajectory planning for meal assist robot considering spilling avoidance”, 2008 IEEE International Conference on Control Applications, pp. 1220-1225, 2008.