Learning from demonstration allows for rapid deployment of robot manipulators to a great many tasks, by relying on a person showing the robot what to do rather than programming it. While this approach provides many opportunities, measuring, evaluating, and improving the person’s teaching ability has remained largely unexplored in robot manipulation research. To this end, a model for learning from demonstration is presented here that incorporates the teacher’s understanding of, and influence on, the learner. The proposed model is used to clarify the teacher’s objectives during learning from demonstration, providing new views on how teaching failures and efficiency can be defined. The benefit of this approach is shown in two experiments ( and , respectively), which highlight the difficulty teachers have in providing effective demonstrations, and show how –180% improvement in teaching efficiency can be achieved through evaluation and feedback shaped by the proposed framework, relative to unguided teaching.
AbbeelPNgAY (2004) Apprenticeship learning via inverse reinforcement learning. In: Twenty-First International Conference on Machine Learning (ICML) ’04. New York: ACM Press.
2.
AhmadzadehSRChernovaS (2018) Trajectory-based skill learning using generalized cylinders. Frontiers in Robotics and AI5: 132.
3.
AhmadzadehSRPaikanAMastrogiovanniFNataleLKormushevPCaldwellDG (2015) Learning symbolic representations of actions from human demonstrations. In: IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp. 3801–3808.
4.
ArgallBBrowningBVelosoM (2007) Learning by demonstration with critique from a human teacher. In: Proceeding of the ACM/IEEE International Conference on Human–Robot Interaction (HRI). New York: ACM Press, p. 57.
5.
ArgallBDChernovaSVelosoMBrowningB (2009) A survey of robot learning from demonstration. Robotics and Autonomous Systems57(5): 469–483.
6.
AsfourTGyarfasFAzadPDillmannR (2006) Imitation learning of dual-arm manipulation tasks in humanoid robots. In: 6th IEEE-RAS International Conference on Humanoid Robots (Humanoids). IEEE, pp. 40–47.
7.
BalbachFJZeugmannT (2009) Recent developments in algorithmic teaching. In: Language and Automata Theory and Applications (LATA). Berlin: Springer, pp. 1–18.
8.
BillardACalinonSDillmannRSchaalS (2008) Robot programming by demonstration. In: Springer Handbook of Robotics. Berlin: Springer, pp. 1371–1394.
9.
BillingEAHellströmT (2010) A formalism for learning from demonstration. Paladyn, Journal of Behavioral Robotics1(1): 1–13.
10.
CakmakMThomazAL (2011) Active learning with mixed query types in learning from demonstration. In: Proceedings of the ICML Workshop on New Developments in Imitation Learning.
11.
CakmakMThomazAL (2014) Eliciting good teaching from humans for machine learners. Artificial Intelligence217: 198–215.
12.
CalinonS (2015) A tutorial on task-parameterized movement learning and retrieval. Intelligent Service Robotics9(1): 1–29.
13.
CalinonSBillardA (2007a) Incremental learning of gestures by imitation in a humanoid robot. In: Proceeding of the ACM/IEEE International Conference on Human–Robot Interaction (HRI). New York: ACM Press, p. 255.
14.
CalinonSBillardA (2007b) What is the teacher’s role in robot programming by demonstration? - Toward benchmarks for improved learning. Interaction Studies8(3): 441–464.
15.
CalinonSLeeD (2017) Learning control. In: Humanoid Robotics: A Reference. Dordrecht: Springer, pp. 1–52.
16.
CederborgTMing LiMBaranesAOudeyerPY (2010) Incremental local online Gaussian mixture regression for imitation learning of multiple tasks. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, pp. 267–274.
17.
CederborgTOudeyerPY (2014) A social learning formalism for learners trying to figure out what a teacher wants them to do. Paladyn, Journal of Behavioral Robotics5(1): pjbr-2014-0005.
18.
ChernovaSThomazAL (2014) Robot Learning from Human Teachers. Morgan & Claypool Publishers.
19.
ChoSJoS (2013) Incremental online learning of robot behaviors from selected multiple kinesthetic teaching trials. IEEE Transactions on Systems, Man, and Cybernetics: Systems43(3): 730–740.
20.
FaulFErdfelderEBuchnerALangA (2009) Statistical power analyses using G*Power 3.1: Tests for correlation and regression analyses. Behavior Research Methods41: 1149–1160.
21.
GoldmanSKearnsM (1995) On the complexity of teaching. Journal of Computer and System Sciences50(1): 20–31.
22.
GoodrichMASchultzAC (2007) Human–robot interaction: A survey. Foundations and Trends® in Human-Computer Interaction1(3): 203–275.
23.
GrollmanDHBillardAG (2012) Robot learning from failed demonstrations. International Journal of Social Robotics4(4): 331–342.
24.
GrothCHenrichD (2014) One-shot robot programming by demonstration using an online oriented particles simulation. In: IEEE International Conference on Robotics and Biomimetics (ROBIO). IEEE, pp. 154–160.
25.
HellströmTBenschS (2018) Understandable robots - what, why, and how. Paladyn, Journal of Behavioral Robotics9(1): 110–123.
26.
HiattLMNarberCBekeleEKhemlaniSSTraftonJG (2017) Human modeling for human–robot collaboration. The International Journal of Robotics Research36(5–7): 580–596.
27.
HoyosJPrietoFAlenyàG, et al. (2016) Incremental learning of skills in a task-parameterized Gaussian mixture model. Journal of Intelligent Robot Systems82: 81–99.
28.
HuangYSilverioJRozoLCaldwellDG (2018) Generalized task-parameterized skill learning. In: IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp. 1–5.
29.
KhanFMutluBZhuX (2011) How do humans teach: On curriculum learning and teaching dimension. Neural Information Processing Systems24: 1449–1457.
30.
KormushevPCalinonSCaldwellD (2013) Reinforcement learning in robotics: Applications and real-world challenges. Robotics2(3): 122–148.
31.
LewisMSycaraKWalkerP (2018) The Role of Trust in Human–Robot Interaction. Cham: Springer, pp. 135–159.
32.
MaedaGEwertonMOsaTBuschBPetersJ (2017) Active incremental learning of robot movement primitives. In: Conference on Robot Learning (CoRL).
33.
NgAYRussellSJ (2000) Algorithms for inverse reinforcement learning. In: Proceedings of the Seventeenth International Conference on Machine Learning (ICML). San Mateo, CA: Morgan Kaufmann, pp. 663–670.
34.
NicolescuMNMataricMJ (2003) Natural methods for robot task learning. In: Proceedings of the 2nd International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS). New York: ACM Press, p. 241.
NikolaidisSZhuYXHsuDSrinivasaS (2017) Human–robot mutual adaptation in shared autonomy. In: ACM/IEEE International Conference on Human–Robot Interaction (HRI). New York: ACM Press, pp. 294–302.
37.
OrendtEMFichtnerMHenrichD (2016) Robot programming by non-experts: Intuitiveness and robustness of One-Shot robot programming. In: 25th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN). IEEE, pp. 192–199.
38.
PervezALeeD (2017) Learning task-parameterized dynamic movement primitives using mixture of GMMs. Intelligent Service Robotics11(1): 61–78.
39.
SchaalS (1997) Learning from demonstration. Neural Information Processing Systems9: 1040–1046.
40.
SchaalS (2006) Dynamic movement primitives - a framework for motor control in humans and humanoid robotics. In: Adaptive Motion of Animals and Machines. Tokyo: Springer-Verlag, pp. 261–280.
41.
SchmiderEZieglerMDanayEBeyerLBühnerM (2010) Is it really robust?Methodology6(4): 147–151.
42.
SenaAZhaoYHowardMJ (2018) Teaching human teachers to teach robot learners. In: IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp. 1–7.
43.
TorisRSuayHBChernovaS (2012) A practical comparison of three robot learning from demonstration algorithms. In: ACM/IEEE International Conference on Human–Robot Interaction (HRI). New York: ACM Press, p. 261.
44.
TykalMMontebelliAKyrkiV (2016) Incrementally assisted kinesthetic teaching for programming by demonstration. In: ACM/IEEE International Conference on Human–Robot Interaction (HRI). IEEE, pp. 205–212.
45.
UrecheALPUmezawaKNakamuraYBillardA (2015) Task parameterization using continuous constraints extracted from human demonstrations. IEEE Transactions on Robotics31(6): 1458–1471.
46.
WeissAIgelsbockJCalinonSBillardATscheligiM (2009) Teaching a humanoid: A user study on learning by demonstration with HOAP-3. In: The 18th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN). IEEE, pp. 147–152.
47.
YangXJUnhelkarVVLiKShahJA (2017) Evaluating effects of user experience and system transparency on trust in automation. In: ACM/IEEE International Conference on Human–Robot Interaction (HRI). New York: ACM Press, pp. 408–416.
48.
ZangPTianRThomazALIsbellCL (2010) Batch versus interactive learning by demonstration. In: IEEE International Conference on Development and Learning (ICDL). IEEE, pp. 219–224.
49.
ZhuX (2015) Machine teaching: an inverse problem to machine learning and an approach toward optimal education. In: Proceedings of the Twenty-Ninth Conference on Artificial Intelligence (AAAI). AAAI Press.
