tailieunhanh - Robotics 2010 Current and future challenges Part 12

Tham khảo tài liệu 'robotics 2010 current and future challenges part 12', kỹ thuật - công nghệ, cơ khí - chế tạo máy phục vụ nhu cầu học tập, nghiên cứu và làm việc hiệu quả | Towards multimodal interface for interactive robots challenges and robotic systems description 375 The human user command The JIDO action Demonstrated modules Comments 1. Hello 1 am here accompanied with a symbolic gesture Local motion towards the user RECO GEST FUSION MHP PSP J IDO moves and stops in front of the user 2. Hi JIDO it s Brice RECO ICU The user must be identified to be granted to interact with J IDO Come to me with a pointing gesture Location mo-tion towards the pointed location on the floor GEST IaECO FUSION MHP The corììíììaỉìd exe_ cution requires the 3D location of the user 4. Stop with a symbolic gesture Stop of the robot GEST RECO FUSION This command is performed while the robot is moving 5. Take this object with a pointing gesture Grasping of the object GEST RECO FUSION Hue- Blob MHP Xarm Jido searches for an object the user points to then picks it up 6. Go to my left side with a pointing gesture Local motion according to the user location GEST RECO FUSION MHP PSP The command execution requires the 3D location of the user 7. Give the object to me Object handling GEST RECO FUSION MHP Xarm The command execution requires no gesture recognition but only the hand tracking 8. Go away with a symbolic gesture Local motion to go away from the user GEST RECO FUSION MHP Table 1. Excerpt of an interaction scenario between a human user and JIDO. 376 Robotics 2010 Current and Future Challenges Fig. 3. From top-left to bottom-right snapshots of a scenario involving speech and gesture recognition and data fusion current H R situation -main frame- GEST module results -bottom right then bottom left- other modules Hue Blob ICU results -top-. Given this scenario quantitative performance evaluations were also conducted. They refer to both i the robot capability to execute the scenario ii and potential user acceptance of the ongoing interaction scenario. The less failures of the multimodal interface will occur the more comfortable the interaction act will be for the