Papers
Topics
Authors
Recent
AI Research Assistant
AI Research Assistant
Well-researched responses based on relevant abstracts and paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses.
Gemini 2.5 Flash
Gemini 2.5 Flash 77 tok/s
Gemini 2.5 Pro 52 tok/s Pro
GPT-5 Medium 30 tok/s Pro
GPT-5 High 31 tok/s Pro
GPT-4o 91 tok/s Pro
Kimi K2 178 tok/s Pro
GPT OSS 120B 385 tok/s Pro
Claude Sonnet 4 38 tok/s Pro
2000 character limit reached

HARMONIOUS -- Human-like reactive motion control and multimodal perception for humanoid robots (2312.02711v2)

Published 5 Dec 2023 in cs.RO

Abstract: For safe and effective operation of humanoid robots in human-populated environments, the problem of commanding a large number of Degrees of Freedom (DoF) while simultaneously considering dynamic obstacles and human proximity has still not been solved. We present a new reactive motion controller that commands two arms of a humanoid robot and three torso joints (17 DoF in total). We formulate a quadratic program that seeks joint velocity commands respecting multiple constraints while minimizing the magnitude of the velocities. We introduce a new unified treatment of obstacles that dynamically maps visual and proximity (pre-collision) and tactile (post-collision) obstacles as additional constraints to the motion controller, in a distributed fashion over the surface of the upper body of the iCub robot (with 2000 pressure-sensitive receptors). This results in a bio-inspired controller that: (i) gives rise to a robot with whole-body visuo-tactile awareness, resembling peripersonal space representations, and (ii) produces human-like minimum jerk movement profiles. The controller was extensively experimentally validated, including a physical human-robot interaction scenario.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. H. A. Park, M. A. Ali, and C. S. G. Lee, “Closed-form inverse kinematic position solution for humanoid robots,” International Journal of Humanoid Robotics, vol. 9, no. 3, p. 1250022, 2012.
  2. P. Beeson and B. Ames, “TRAC-IK: An open-source library for improved solving of generic inverse kinematics,” in 2015 IEEE-RAS International Conference on Humanoid Robots, 2015, pp. 928–935.
  3. S. Lloyd, R. A. Irani, and M. Ahmadi, “Fast and Robust Inverse Kinematics of Serial Robots Using Halley’s Method,” IEEE Transactions on Robotics, vol. 38, no. 5, pp. 2768–2780, Oct. 2022.
  4. U. Pattacini, F. Nori, L. Natale, G. Metta, and G. Sandini, “An experimental evaluation of a novel minimum-jerk cartesian controller for humanoid robots,” in 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Oct. 2010, pp. 1668–1674.
  5. K. Glass, R. Colbaugh, D. Lim, and H. Seraji, “Real-Time Collision Avoidance for Redundant Manipulators,” IEEE Transactions on Robotics and Automation, vol. 11, no. 3, pp. 448–457, 1995.
  6. D. H. Park, H. Hoffmann, P. Pastor, and S. Schaal, “Movement reproduction and obstacle avoidance with dynamic movement primitives and potential fields,” in 2008 IEEE-RAS International Conference on Humanoid Robots, 2008, pp. 91–98.
  7. F. Flacco, T. Kröger, A. De Luca, and O. Khatib, “A depth space approach to human-robot collision avoidance,” in 2012 IEEE International Conference on Robotics and Automation, 2012, pp. 338–345.
  8. J. Haviland and P. Corke, “NEO: A novel expeditious optimisation algorithm for reactive motion control of manipulators,” IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 1043–1050, Apr. 2021.
  9. C. Escobedo, M. Strong, M. West, A. Aramburu, and A. Roncone, “Contact Anticipation for Physical Human–Robot Interaction with Robotic Manipulators using Onboard Proximity Sensors,” in 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems, Sep. 2021, pp. 7255–7262.
  10. Y. Ding and U. Thomas, “Collision Avoidance with Proximity Servoing for Redundant Serial Robot Manipulators,” in 2020 IEEE International Conference on Robotics and Automation, May 2020, pp. 10 249–10 255.
  11. D. Guo and Y. Zhang, “A New Inequality-Based Obstacle-Avoidance MVN Scheme and Its Application to Redundant Robot Manipulators,” IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), vol. 42, no. 6, pp. 1326–1340, Nov. 2012.
  12. Y. Tong, J. Liu, X. Zhang, and Z. Ju, “Four-Criterion-Optimization-Based Coordination Motion Control of Dual-Arm Robots,” IEEE Transactions on Cognitive and Developmental Systems, vol. 15, no. 2, pp. 794–807, 2023.
  13. W. Suleiman, “On inverse kinematics with inequality constraints: New insights into minimum jerk trajectory generation,” Advanced Robotics, vol. 30, no. 17-18, pp. 1164–1172, Sep. 2016.
  14. D. Rakita, H. Shi, B. Mutlu, and M. Gleicher, “Collisionik: A per-instant pose optimization method for generating robot motions with environment collision avoidance,” in 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021, pp. 9995–10 001.
  15. O. Khatib, “Real-Time Obstacle Avoidance for Manipulators and Mobile Robots,” Autonomous Robot Vehicles, pp. 396–404, 1986.
  16. K. Merckaert, B. Convens, C. ju Wu, A. Roncone, M. M. Nicotra, and B. Vanderborght, “Real-time motion control of robotic manipulators for safe human–robot coexistence,” Robotics and Computer-Integrated Manufacturing, vol. 73, p. 102223, Feb. 2022.
  17. P. D. Nguyen, F. Bottarel, U. Pattacini, M. Hoffmann, L. Natale, and G. Metta, “Merging Physical and Social Interaction for Effective Human-Robot Collaboration,” in 2018 IEEE-RAS International Conference on Humanoid Robots, 2018, pp. 710–717.
  18. J. Schulman, J. Ho, A. Lee, I. Awwal, H. Bradlow, and P. Abbeel, “Finding Locally Optimal, Collision-Free Trajectories with Sequential Convex Optimization,” in Robotics: Science and Systems IX, 2013, pp. 1–10.
  19. S. Zimmermann, M. Busenhart, S. Huber, R. Poranne, and S. Coros, “Differentiable Collision Avoidance Using Collision Primitives,” in 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, Oct. 2022, pp. 8086–8093.
  20. R. Bordalba, T. Schoels, L. Ros, J. M. Porta, and M. Diehl, “Direct collocation methods for trajectory optimization in constrained robotic systems,” IEEE Transactions on Robotics, vol. 39, no. 1, pp. 183–202, 2023.
  21. D. E. Whitney, “Resolved Motion Rate Control of Manipulators and Human Prostheses,” IEEE Transactions on Man-Machine Systems, vol. 10, no. 2, pp. 47–53, 1969.
  22. A. Albini, F. Grella, P. Maiolino, and G. Cannata, “Exploiting Distributed Tactile Sensors to Drive a Robot Arm through Obstacles,” IEEE Robotics and Automation Letters, vol. 6, no. 3, pp. 4361–4368, Jul. 2021.
  23. A. Cirillo, F. Ficuciello, C. Natale, S. Pirozzi, and L. Villani, “A conformable force/tactile skin for physical human-robot interaction,” IEEE Robotics and Automation Letters, vol. 1, no. 1, pp. 41–48, Jan. 2016.
  24. E. Magrini and A. De Luca, “Hybrid force/velocity control for physical human-robot collaboration tasks,” in 2016 IEEE International Conference on Intelligent Robots and Systems, Nov. 2016, pp. 857–863.
  25. N. Mansard, O. Stasse, P. Evrard, and A. Kheddar, “A versatile generalized inverted kinematics implementation for collaborative working humanoid robots: The stack of tasks,” in International Conference on Advanced Robotics (ICAR), June 2009, p. 119.
  26. C. Escobedo, N. Nechyporenko, S. Kadekodi, and A. Roncone, “A Framework for the Systematic Evaluation of Obstacle Avoidance and Object-Aware Controllers,” in 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2022, pp. 8117–8124.
  27. Y. Nakamura and H. Hanafusa, “Inverse Kinematic Solutions With Singularity Robustness for Robot Manipulator Control,” Journal of Dynamic Systems, Measurement, and Control, vol. 108, no. 3, pp. 163–171, 09 1986.
  28. A. Dietrich, T. Wimböck, A. Albu-Schäffer, and G. Hirzinger, “Reactive whole-body control: Dynamic mobile manipulation using a large number of actuated degrees of freedom,” IEEE Robotics and Automation Magazine, vol. 19, no. 2, pp. 20–33, 2012.
  29. S. Haddadin, H. Urbanek, S. Parusel, D. Burschka, J. Roßmann, A. Albu-Schäffer, and G. Hirzinger, “Real-time reactive motion generation based on variable attractor dynamics and shaped velocities,” in 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2010, pp. 3109–3116.
  30. D. H. P. Nguyen, M. Hoffmann, A. Roncone, U. Pattacini, and G. Metta, “Compact Real-time Avoidance on a Humanoid Robot for Human-robot Interaction,” in ACM/IEEE International Conference on Human-Robot Interaction, Feb. 2018, pp. 416–424.
  31. A. Lambert, M. Mukadam, B. Sundaralingam, N. Ratliff, B. Boots, and D. Fox, “Joint Inference of Kinematic and Force Trajectories with Visuo-Tactile Sensing,” in 2019 International Conference on Robotics and Automation, 2019.
  32. K. He, R. Newbury, T. Tran, J. Haviland, B. Burgess-Limerick, D. Kulić, P. Corke, and A. Cosgun, “Visibility Maximization Controller for Robotic Manipulation,” IEEE Robotics and Automation Letters, vol. 7, no. 3, pp. 8479–8486, Jul. 2022.
  33. D. Kulić and E. A. Croft, “Real-time safety for human–robot interaction,” Robotics and Autonomous Systems, vol. 54, no. 1, pp. 1–12, Jan. 2006.
  34. J. Docekal, J. Rozlivek, J. Matas, and M. Hoffmann, “Human keypoint detection for close proximity human-robot interaction,” in 2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids), 2022, pp. 450–457.
  35. E. Aljalbout, J. Chen, K. Ritt, M. Ulmer, and S. Haddadin, “Learning Vision-based Reactive Policies for Obstacle Avoidance,” in Proceedings of the 2020 Conference on Robot Learning.   PMLR, 2020, pp. 2040–2054.
  36. S. Haddadin, A. De Luca, and A. Albu-Schäffer, “Robot collisions: A survey on detection, isolation, and identification,” IEEE Transactions on Robotics, vol. 33, no. 6, pp. 1292 – 1312, 2017.
  37. R. Calandra, S. Ivaldi, M. P. Deisenroth, and J. Peters, “Learning torque control in presence of contacts using tactile sensing from robot skin,” in 2015 IEEE-RAS International Conference on Humanoid Robots, 2015, pp. 690–695.
  38. A. Albini, S. Denei, and G. Cannata, “Enabling natural human-robot physical interaction using a robotic skin feedback and a prioritized tasks robot control architecture,” in 2017 IEEE-RAS International Conference on Humanoid Robots, 2017, pp. 99–106.
  39. J. Kuehn and S. Haddadin, “An Artificial Robot Nervous System to Teach Robots How to Feel Pain and Reflexively React to Potentially Damaging Contacts,” IEEE Robotics and Automation Letters, vol. 2, no. 1, pp. 72–79, Jan. 2017.
  40. P. Svarny, J. Rozlivek, L. Rustler, M. Sramek, Özgür Deli, M. Zillich, and M. Hoffmann, “Effect of active and passive protective soft skins on collision forces in human–robot collaboration,” Robotics and Computer-Integrated Manufacturing, vol. 78, p. 102363, 2022.
  41. F. Flacco and A. De Luca, “Real-time computation of distance to dynamic obstacles with multiple depth sensors,” IEEE Robotics and Automation Letters, vol. 2, no. 1, pp. 56–63, 2016.
  42. S. Mühlbacher-Karrer, M. Brandstötter, D. Schett, and H. Zangl, “Contactless Control of a Kinematically Redundant Serial Manipulator Using Tomographic Sensors,” IEEE Robotics and Automation Letters, vol. 2, no. 2, pp. 562–569, Apr. 2017.
  43. A. Roncone, M. Hoffmann, U. Pattacini, L. Fadiga, and G. Metta, “Peripersonal Space and Margin of Safety around the Body: Learning Visuo-Tactile Associations in a Humanoid Robot with Artificial Skin,” PLOS ONE, vol. 11, no. 10, pp. 1–32, 10 2016.
  44. J. Cléry and S. B. Hamed, “Frontier of self and impact prediction,” Frontiers in psychology, vol. 9, p. 1073, 2018.
  45. A. Roncone, M. Hoffmann, U. Pattacini, and G. Metta, “Learning peripersonal space representation through artificial skin for avoidance and reaching with whole body surface,” in 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2015, pp. 3366–3373.
  46. G. Metta, L. Natale, F. Nori, G. Sandini, D. Vernon, L. Fadiga, C. von Hofsten, K. Rosander, M. Lopes, J. Santos-Victor, A. Bernardino, and L. Montesano, “The iCub humanoid robot: An open-systems platform for research in cognitive development,” Neural Networks, vol. 23, no. 8, pp. 1125–1134, 2010.
  47. P. Maiolino, M. Maggiali, G. Cannata, G. Metta, and L. Natale, “A flexible and robust large scale capacitive tactile system for robots,” IEEE Sensors Journal, vol. 13, no. 10, pp. 3910–3917, 2013.
  48. C. Escobedo and M. Strong, “HIRO Skin Unit,” https://github.com/HIRO-group/skin_unit_setup, 2020.
  49. T. Yoshikawa, “Manipulability of robotic mechanisms,” The International Journal of Robotics Research, vol. 4, no. 2, pp. 3–9, 1985.
  50. T. Flash and N. Hogan, “The coordination of arm movements: an experimentally confirmed mathematical model,” Journal of Neuroscience, vol. 5, no. 7, pp. 1688–1703, 1985.
  51. R. Shadmehr and S. Wise, “Supplementary documents for “computational neurobiology of reaching and pointing”,” https://storage.googleapis.com/wzukusers/user-31382847/documents/5a7253343814f4Iv6Hnt/minimumjerk.pdf, 2005, accessed: October 13, 2023.
  52. K. Shoemake, “Animating rotation with quaternion curves,” SIGGRAPH Comput. Graph., vol. 19, no. 3, p. 245–254, jul 1985.
  53. A. Roncone, U. Pattacini, G. Metta, and L. Natale, “A Cartesian 6-DoF Gaze Controller for Humanoid Robots,” in Proceedings of Robotics: Science and Systems, AnnArbor, Michigan, June 2016.
Citations (1)

Summary

  • The paper introduces HARMONIOUS, a motion controller that enables humanoid robots to navigate human-populated environments with 17 degrees of freedom.
  • It employs quadratic programming to balance joint velocities, natural postures, and real-time collision avoidance using multimodal sensory inputs.
  • Real-world tests with the iCub robot demonstrate the system’s robustness and practical applicability in dynamic, cluttered settings.

Introduction to Humanoid Robots and HARMONIOUS

Humanoid robots are advanced robotic systems designed to mimic human form and behavior, which makes them suitable for a wide range of tasks that involve interacting with humans or operating in environments built for people. To be effective, these robots must be capable of moving smoothly and avoiding obstacles, including dynamic ones like humans moving in their vicinity. However, ensuring that a humanoid robot can navigate such complex environments safely and effectively has been a challenging goal for roboticists.

HARMONIOUS: A New Reactive Motion Controller

A significant advancement in this area is the HARMONIOUS system, which stands for "Human-like reactive motion control and multimodal perception for humanoid robots." HARMONIOUS is a reactive motion controller tailored for humanoid robots that must operate amidst human-populated spaces. Unlike traditional robot controllers, HARMONIOUS can command the upper body of a humanoid robot, including two arms and a torso, summing up to a total of 17 degrees of freedom (DoF).

The core of HARMONIOUS is a quadratic programming approach that balances multiple factors including minimizing joint velocities, rewarding natural postures, and dampening motion in the vicinity of kinematic singularities—all while handling real-time collision avoidance.

Collision Avoidance and Obstacle Handling

A unique aspect of HARMONIOUS is its ability to handle obstacles using a unified treatment of multimodal sensory inputs that includes visual, proximity, and tactile information. The system can dynamically process signals from RGB-D cameras, proximity sensors, and a network of 2000 pressure-sensitive tactile receptors, transforming them into real-time constraints on the motion controller. This fusion of data creates a protective safety margin, similar to the concept of peripersonal space in humans, where the robot maintains awareness of its surroundings and can react to avoid obstacles and collisions.

Human-like Motion and Adaptability

HARMONIOUS stands out due to its bio-inspired movement profiles that mimic human motion patterns, such as minimum jerk trajectories that create smooth and natural-looking movements. Additionally, the controller's whole-body awareness and responsiveness to dynamic changes in the environment enable it to effectively manage multiple tasks and avoid collisions. This versatility makes HARMONIOUS adaptable for various scenarios, from moving efficiently in cluttered spaces to interacting with humans in shared workplaces.

Real-world Applications and Future Development

The motion control system has been rigorously tested in simulation and with the iCub humanoid robot across different experimental setups, demonstrating superior performance compared to other state-of-the-art approaches. Real-world applications, including a children's board game where the robot had to interact closely with a human player, showcased the system's robustness and practicality.

Moving forward, the development of HARMONIOUS will focus on incorporating active gaze control for better sensory perception and minimizing noise in sensory inputs. Enhancements like these will continue to improve humanoid robots' capabilities, making them valuable partners in everyday settings, contributing to industries, and assisting in personal and domestic environments.

List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets

This paper has been mentioned in 2 posts and received 4 likes.