Anticipatory Planning for Human-Robot Teams
详细信息 查看全文
- 关键词：Collaborative task planning ; Anticipation ; Human activity perception ; Object affordances ; Human ; robot interaction
- 刊名：Springer Tracts in Advanced Robotics
- 出版年：2016
- 出版时间：2016
- 年：2016
- 卷：109
- 期：1
- 页码：453-470
- 全文大小：877 KB
- 参考文献：1.Aksoy, E.E., Abramov, A., Dörr, J., Ning, K., Dellen, B., Wörgötter, F.: Learning the semantics of object-action relations by observation. IJRR 30(10) (2011)
2.Aldoma, A., Tombari, F., Vincze, M.: Supervised learning of hidden and non-hidden 0-order affordances and detection in real scenes. In: ICRA (2012)
3.Bento, J., Derbinsky, N., Alonso-Mora, J., Yedidia, J.S.: A message-passing algorithm for multi-agent trajectory planning. In: NIPS (2013)
4.Busoniu, L., Babuska, R., De Schutter, B.: A comprehensive survey of multiagent reinforcement learning. IEEE SMC Part C (2008)
5.Cakmak, M., Srinivasa, S.S., Lee, M.K., Forlizzi, J.F., Kiesler, S.: Human preferences for robot-human hand-over configurations. In: IROS (2011)
6.Carmel, D., Markovitch, S.: Opponent modeling in multi-agent systems. In: Adaption and Learning In Multi-Agent Systems, vol. 1042 (1996)
7.Diankov, R.: Automated Construction of Robotic Manipulation Programs. Ph.D. thesis, CMU, RI, August 2010
8.Gibson, J.J.: The Ecological Approach to Visual Perception (1979)
9.Hermans, T., Rehg, J.M., Bobick, A.: Affordance prediction via learned object attributes. In: ICRA Workshop on SPME (2011)
10.Hermans, T., Rehg, J.M., Bobick, A.: Decoupling behavior, perception, and control for autonomous learning of affordances. In: ICRA (2013)
11.Hu, J., Wellman, M.P.: Multiagent reinforcement learning: theoretical framework and an algorithm. In: ICML (1998)
12.Jiang, Y., Koppula, H.S., Saxena, A.: Hallucinated humans as the hidden context for labeling 3D scenes. In: CVPR (2013)
13.Kahneman, D.: Thinking, fast and slow (2011)
14.Katz, D., Venkatraman, A., Kazemi, M., Bagnell, J.A., Stentz, A.: Perceiving, learning, and exploiting object affordances for autonomous pile manipulation. In: RSS (2013)
15.Koenig, S., Keskinocak, P., Tovey, C.A.: Progress on agent coordination with cooperative auctions. In: AAAI (2010)
16.Konidaris, G., Kuindersma, S., Grupen, R., Barto, A.: Robot learning from demonstration by constructing skill trees. IJRR 31 (2012)
17.Koppula, H.S., Saxena, A.: Learning spatio-temporal structure from RGB-D videos for human activity detection and anticipation. In: ICML (2013)
18.Koppula, H.S., Saxena, A.: Anticipating human activities using object affordances for reactive robotic response. In: RSS (2013)
19.Koppula, H.S., Saxena, A.: Physically grounded spatio-temporal object affordances. In: ECCV (2014)
20.Koppula, H.S., Gupta, R., Saxena, A.: Learning human activities and object affordances from RGB-D videos. In: IJRR (2013)
21.Lauer, M., Riedmiller, M.: An algorithm for distributed reinforcement learning in cooperative multi-agent systems. In: ICML (2000)
22.Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: ICML (1994)
23.Littman, M.L.: Friend-or-FOE Q-learning in general-sum games. In: ICML (2001)
24.Lopes, M., Santos-Victor, J.: Visual learning by imitation with motor representations. IEEE SMC, Part B (2005)
25.Lorken, C., Hertzberg, J.: Grounding planning operators by affordances. In: International Conference on Cognitive Systems (2008)
26.Mainprice, J., Berenson, D.: Human-robot collaborative manipulation planning using early prediction of human motion. In: IROS (2013)
27.Mainprice, J., Sisbot, E.A., Jaillet, L., Cortés, J., Alami, R., Siméon, T.: Planning human-aware motions using a sampling-based costmap planner. In: ICRA (2011)
28.Meisner, E., Isler, V., Trinkle, J.: Controller design for human-robot interaction. Auton. Robot. 24(2), 123–134 (2008)
29.Moldovan, B., van Otterlo, M., Moreno, P., Santos-Victor, J., De Raedt, L.: Statistical relational learning of object affordances for robotic manipulation. Latest Adv. Inductive Logic Prog. (2012)
30.Montesano, L., Lopes, M., Bernardino, A., Santos-Victor, J.: Learning object affordances: from sensory-motor coordination to imitation. Trans. Robot. 24(1), 15–26 (2008)
31.Nikolaidis, S., Shah, J.: Human-robot teaming using shared mental models. In: HRI, Workshop on Human-Agent-Robot Teamwork (2012)
32.Nikolaidis, S., Shah, J.: Human-robot cross-training: computational formulation, modeling and evaluation of a human team training strategy. In: HRI (2013)
33.Powers, R., Shoham, Y.: New criteria and a new algorithm for learning in multi-agent systems. In: NIPS (2004)
34.Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley, New York (1994)
35.Sisbot, E.A., Marin, L.F., Alami, R.: Spatial reasoning for human robot interaction. In: IROS (2007)
36.Strabala, K.W., Lee, M.K., Dragan, A.D., Forlizzi, J.L., Srinivasa, S.S., Cakmak, M., Micelli, V.: Towards seamless human-robot handovers. JHRI (2013)
37.Sun, J., Moore, J.L., Bobick, A., Rehg, J.M.: Learning visual object categories for robot affordance prediction. IJRR (2009)
38.Tesauro, G.: Extending Q-learning to general adaptive multi-agent systems. In: NIPS (2004)
39.Turpin, M., Michael, N., Kumar, V.: Trajectory planning and assignment in multirobot systems. In: WAFR (2012)
40.Ugur, E., Sachin, E., Oztop, E.: Affordance learning from range data for multi-step planning. In: Epirob (2009)
41.Uyanik, K.F., Caliskan, Y., Bozcuoglu, A.K., Kalkan, S., Yuruten, O., Sahin, E.: Learning social affordances and using them for planning. In: CogSys (2013)
42.Wang, J., Liu, Z., Wu, Y., Yuan, J.: Mining actionlet ensemble for action recognition with depth cameras. In: CVPR (2012)
43.Wongpiromsarn, T., Ulusoy, A., Belta, C., Frazzoli, E., Rus, D.: Incremental synthesis of control policies for heterogeneous multi-agent systems with linear temporal logic specifications. In: ICRA (2013)
44.Wunder, M., Littman, M.L., Babes, M.: Classes of multiagent q-learning dynamics with epsilon-greedy exploration. In: ICML (2010) - 作者单位：Hema S. Koppula (6)
Ashesh Jain (6)
Ashutosh Saxena (6)
6. Department of Computer Science, Cornell University, Ithaca, USA - 丛书名：Experimental Robotics
- ISBN：978-3-319-23778-7
- 刊物类别：Engineering
- 刊物主题：Automation and Robotics
Control Engineering - 出版者：Springer Berlin / Heidelberg
- ISSN：1610-742X
文摘
When robots work alongside humans for performing collaborative tasks, they need to be able to anticipate human’s future actions and plan appropriate actions. The tasks we consider are performed in contextually-rich environments containing objects, and there is a large variation in the way humans perform these tasks. We use a graphical model to represent the state-space, where we model the humans through their low-level kinematics as well as their high-level intent, and model their interactions with the objects through physically-grounded object affordances. This allows our model to anticipate a belief about possible future human actions, and we model the human’s and robot’s behavior through an MDP in this rich state-space. We further discuss that due to perception errors and the limitations of the model, the human may not take the optimal action and therefore we present robot’s anticipatory planning with different behaviors of the human within the model’s scope. In experiments on Cornell Activity Dataset, we show that our method performs better than various baselines for collaborative planning.