A Hybrid Joint/Cartesian DMP-Based Approach for Obstacle Avoidance of Anthropomorphic Assistive Robots
- 27 Downloads
Anthropomorphic criteria are widely adopted for developing socially interactive robots since they can improve human capability to interpret and predict robot motion, with an impact on robot acceptability and human–robot interaction safety. Learning by demonstration approaches based on dynamic movement primitives are a suitable solution for planning the robot motion in human-like fashion and endow robots with generalization capabilities and robustness against perturbation. Objective of this work is to propose a new formulation of the learning by demonstration approach based on dynamic movement primitives (DMPs), called hybrid joint/Cartesian DMPs, for redundant robots with the twofold purpose of avoiding obstacles on the path and obtaining anthropomorphic motion in the joint as well as the task space. The proposed approach, suitable for assistive purposes, was experimentally validated on the anthropomorphic robot arm Kuka Light Weight Robot 4+. Trajectories recorded by an optoelectronic system (i.e. the BTS Smart D) from human demonstrators performing point-to-point reaching and pouring tasks were adopted to teach the robot how to move. A comparative analysis with current methods of learning by demonstration in the literature, i.e. Cartesian DMP and inverse kinematics, was performed. Performance indicators were introduced to (1) assess the robot accuracy of the motion performing, (2) evaluate the level of anthropomorphism of the computed motion, (3) measure the success rate in obstacle avoidance. Moreover, questionnaires were administered to ten human subjects who observed robot motion. The obtained results demonstrated that the proposed approach guarantees anthropomorphic motion of the robot both in the joint and in the task spaces ensuring obstacle avoidance along the robot kinematic chain. In particular, the anthropomorphic robot, while operating with the proposed method, exhibits behaviours in the joint space that are similar to the one recorded during the demonstration and has a level of anthropomorphism rather higher than the one obtained with Cartesian DMP and inverse kinematics (a configuration of the robot joints within the physiological limits is always ensured and the maximum convex hull created between the human and the robot arm is 0.0085 m\(^3\)). In presence of obstacles, an acceptable level of the Cartesian accuracy (\(Position~err<0.005\) m and \(Orientation~err<0.02\) rad) is achieved. The obstacles are avoided with a 100% of success. The questionnaire results showed that the users feel more comfortable and less nervous to interact with a robot that moves in human-like manner.
KeywordsLearning by demonstration Dynamic movement primitives Human-like motion Obstacle avoidance
This study was funded partly by the Campus Bio-Medico University Strategic Projects (Call 2018) with the SAFE-MOVER project, partly by the Italian Ministry of University and Research (PON Project research and innovation 2014–2020) with the ARONA project (CUP: B26G18000390005) and partly by the Italian Institute for Labour Accidents (INAIL) with the RehabRobo@work (CUP: C82F17000040001) and PPR AS 1/3 (CUP: E57B16000160005) projects.
Compliance with Ethical Standards
Conflict of interest
The authors declare that they have no conflict of interest.
- 2.Zollo L, Laschi C, Teti G, Siciliano B, Dario P (2001) Functional compliance in the control of a personal robot. In: Proceedings 2001 IEEE/RSJ international conference on intelligent robots and systems. Expanding the societal role of robotics in the the next millennium (Cat. No. 01CH37180), vol 4. IEEE, pp 2221–2226Google Scholar
- 4.Liarokapis MV, Artemiadis PK, Kyriakopoulos KJ (2012) Functional anthropomorphism for human to robot motion mapping. In: RO-MAN. IEEE, pp 31–36Google Scholar
- 5.Hegel F, Krach S, Kircher T, Wrede B, Sagerer G (2008) Understanding social robots: a user study on anthropomorphism. In: Robot and human interactive communication. In: The 17th IEEE international symposium on RO-MAN 2008, pp 574–579. IEEEGoogle Scholar
- 8.Duffy BR (2002) Anthropomorphism and robotics. In: The society for the study of artificial intelligence and the simulation of behaviour, vol 20. CiteseerGoogle Scholar
- 9.Formica D, Zollo L, Guglielmelli E (2005) Torque-dependent compliance control in the joint space of an operational robotic machine for motor therapy. In 9th International conference on rehabilitation robotics. ICORR 2005. IEEE, pp 341–344Google Scholar
- 10.Riek LD, Rabinowitch TC, Chakrabarti B, Robinson P (2009) How anthropomorphism affects empathy toward robots. In: Proceedings of the 4th ACM/IEEE international conference on human–robot interaction. ACM, pp 245–246Google Scholar
- 11.Lasota PA, Rossano GF, Shah JA (2014) Toward safe close-proximity human-robot interaction with standard industrial robots. In: 2014 IEEE international conference on automation science and engineering (CASE). IEEE, pp 339–344Google Scholar
- 14.Pastor P, Hoffmann H, Asfour T, Schaal S (2009) Learning and generalization of motor skills by learning from demonstration. In: IEEE international conference on robotics and automation. ICRA’09. IEEE, pp 763–768Google Scholar
- 16.Hoffmann H, Pastor P, Park DH, Schaal S (2009) Biologically-inspired dynamical systems for movement generation: automatic real-time goal adaptation and obstacle avoidance. In: IEEE international conference on robotics and automation. ICRA’09. IEEE, pp 2587–2592Google Scholar
- 17.Tan H, Erdemir E, Kawamura K, Du Q (2011) A potential field method-based extension of the dynamic movement primitive algorithm for imitation learning with obstacle avoidance. In: International conference on mechatronics and automation (ICMA). IEEE, pp 525–530Google Scholar
- 18.Park DH, Hoffmann H, Pastor P, Schaal S (2008) Movement reproduction and obstacle avoidance with dynamic movement primitives and potential fields. In: 8th IEEE-RAS international conference on humanoid robots. Humanoids 2008. IEEE, pp 91–98Google Scholar
- 20.Rai A, Meier F, Ijspeert A, Schaal S (2014) Learning coupling terms for obstacle avoidance. In: 14th IEEE-RAS international conference on humanoid robots (Humanoids). IEEE, pp 512–518Google Scholar
- 21.Iossifidis I, Schoner G (2006) Dynamical systems approach for the autonomous avoidance of obstacles and joint-limits for an redundant robot arm. In: IEEE/RSJ international conference on intelligent robots and systems. IEEE, pp 580–585Google Scholar