Nonmyopic view planning for active object classification and pose estimation

IEEE Transactions on Robotics

Volumn 30, Issue 5, 2014, Pages 1078-1090

  Atanasov, Nikolay ^a   Sankaran, Bharath ^b   Le Ny, Jerome ^c,d   Pappas, George J ^a   Daniilidis, Kostas ^a  

^a UNIVERSITY OF PENNSYLVANIA   (United States)

^b UNIVERSITY OF SOUTHERN CALIFORNIA   (United States)

^c ÉCOLE POLYTECHNIQUE DE MONTRÉAL   (Canada)

^d GERAD   (Canada)

Author keywords

Active object classification and pose estimation; hypothesis testing; motion control; planning and control for mobile sensors; recognition; robotics; vocabulary tree

Indexed keywords

ROBOTICS;

HYPOTHESIS TESTING; MOBILE SENSORS; POSE ESTIMATION; RECOGNITION; VOCABULARY TREE;

MOTION CONTROL;

EID: 84907845680     PISSN: 15523098     EISSN: None     Source Type: Journal    
DOI: 10.1109/TRO.2014.2320795     Document Type: Article

References (39)

1. D. Lowe, "Distinctive image features from scale-invariant keypoints," Int. J. Comput. Vis., vol. 60, no. 2, pp. 91-110, 2004.
2. S. Belongie, J. Malik, and J. Puzicha, "Shape matching and object recognition using shape contexts," IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, no. 4, pp. 509-522, Apr. 2002.
3. T.-J. Fan, G. Medioni, and R. Nevatia, "Recognizing 3-D objects using surface descriptions," IEEE Trans. Pattern Anal. Mach. Intell., vol. 11, no. 11, pp. 1140-1157, Nov. 1989.
4. A. Hero, III and D. Cochran, "Sensor management: Past, present, and future," IEEE Sensors J., vol. 11, no. 12, pp. 3064-3075, Dec. 2011.
5. M. Spaan, T. Veiga, and P. Lima, "Active cooperative perception in network robot systems using POMDPs," in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., 2010, pp. 4800-4805.
6. K. Jenkins, "Fast adaptive sensor management for feature-based classification," Ph.D. dissertation, Dept. Elect. Eng., Boston Univ., Boston, MA, USA, 2010.
7. C. Kreucher, K. Kastella, and A. Hero, III, "Sensor management using an active sensing approach," Signal Process., vol. 85, no. 3, pp. 607-624, 2005.
8. E. Sommerlade and I. Reid, "Information theoretic active scene exploration," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2008, pp. 1-7.
9. R. Rusu and S. Cousins, "3D is here: Point cloud library (PCL)," in Proc. IEEE Int. Conf. Robot. Autom., 2011, pp. 1-4.
10. N. Atanasov, B. Sankaran, J. Le Ny, T. Koletschka, G. Pappas, and K. Daniilidis, "Hypothesis testing framework for active object detection," in Proc. IEEE Int. Conf. Robot. Autom., 2013, pp. 4216-4222.
11. R. Bajcsy, "Active perception," Proc. IEEE, vol. 76, no. 8, pp. 966-1005, Aug. 1988.
12. E. Krotkov and R. Bajcsy, "Active vision for reliable ranging: Cooperating focus, stereo, and vergence," Int. J. Comput. Vis., vol. 11, no. 2, pp. 187-203, 1993.
13. R. Pito, "A solution to the next best view problem for automated surface acquisition," IEEE Trans. Pattern Anal. Mach. Intell., vol. 21, no. 10, pp. 1016-1030, Oct. 1999.
14. M. Huber, "Probabilistic framework for sensor management," Ph.D. dissertation, Fakultät für Informatik, Univ. Karlsruhe, Karlsruhe, Germany, 2009.
15. B. Browatzki, V. Tikhanoff, G. Metta, H. Bulthoff, and C. Wallraven, "Active object recognition on a humanoid robot," in Proc. IEEE Int. Conf. Robot. Autom., 2012, pp. 2021-2028.
16. H. Borotschnig, L. Paletta, M. Prantl, and A. Pinz, "Appearance-based active object recognition," Image Vis. Comput., vol. 18, no. 9, pp. 715-727, 2000.
17. C. Potthast and G. Sukhatme, "A probabilistic framework for next best view estimation in a cluttered environment," J. Vis. Commun. Image Represent., vol. 25, no. 1, pp. 148-164, 2014.
18. J. Denzler and C. Brown, "Information theoretic sensor data selection for active object recognition and state estimation," IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, no. 2, pp. 145-157, Feb. 2002.
19. S. Ekvall, P. Jensfelt, andD.Kragic, "Integrating active mobile robot object recognition and SLAM in natural environments," in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., 2006, pp. 5792-5797.
20. D. Golovin and A. Krause, "Adaptive submodularity: Theory and applications in active learning and stochastic optimization," J. Artif. Intell. Res., vol. 42, no. 1, pp. 427-486, 2011.
21. A. Krause, A. Singh, and C. Guestrin, "Near-optimal sensor placements in Gaussian processes: Theory, efficient algorithms and empirical studies," J. Mach. Learn. Res., vol. 9, pp. 235-294, 2008.
22. A. Krause, "Optimizing sensing: Theory and applications," Ph.D. dissertation, Dept. Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA, 2008.
23. V. Karasev, A. Chiuso, and S. Soatto, "Controlled recognition bounds for visual learning and exploration," Proc. Adv. Neural Inf. Process. Syst., pp. 2915-2923, 2012.
24. M. Naghshavar and T. Javidi, "Active sequential hypothesis testing," Ann. Stat., vol. 41, no. 6, pp. 2703-2738, 2013.
25. H. Kurniawati, D. Hsu, and W. Lee, "SARSOP: Efficient point-based POMDP planning by approximating optimally reachable belief spaces," in Proc. Robot.: Sci. Syst., Zurich, Switzerland, Jun. 2008. Available: http://www.roboticsproceedings.org/rss04/p9.html
26. S. Ong, S. Png, D. Hsu, and W. Lee, "POMDPs for robotic tasks with mixed observability," in Proc. Robot.: Sci. Syst., Seattle, USA, Jun. 2009. Available: http://www.roboticsproceedings.org/rss05/p26.html.
27. R. Eidenberger and J. Scharinger, "Active perception and scene modeling by planning with probabilistic 6D object poses," in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., 2010, pp. 1036-1043.
28. L. Paletta and A. Pinz, "Active object recognition by view integration and reinforcement learning," Robot. Auton. Syst., vol. 31, no. 1-2, pp. 71-86, 2000.
29. J. Velez, G. Hemann, A. Huang, I. Posner, and N. Roy, "Modelling observation correlations for active exploration and robust object detection," J. Artif. Intell. Res., vol. 44, pp. 424-453, 2012.
30. P. Felzenszwalb, R. Girshick, and D. McAllester, "A discriminatively trained, multiscale, deformable part model," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2008, pp. 1-8.
31. B. Sankaran, Sequential hypothesis testing for next best view estimation," Master's thesis,Dept. Comput. Inf. Sci.,Univ. Pennsylvania, Philadelphia, PA, USA, 2012.
32. C. Laporte and T. Arbel, "Efficient discriminant viewpoint selection for active Bayesian recognition," Int. J. Comput. Vis., vol. 68, no. 3, pp. 267-287, 2006.
33. M. Hanheide, C. Gretton, R. Dearden, N. Hawes, J. Wyatt, A. Pronobis, A. Aydemir, M. Göbelbecker, and H. Zender, "Exploiting probabilistic knowledge under uncertain sensing for efficient robot behaviour," in Proc. Int. Joint Conf. Artif. Intell., 2011, pp. 2442-2449.
34. M. Göbelbecker, C. Gretton, and R. Dearden, "A switching planner for combined task and observation planning," in Proc. AAAI Conf. Artif. Intell., 2011.
35. A. Aydemir, K. Sjöo, J. Folkesson, A. Pronobis, and P. Jensfelt, "Search in the real world: Active visual object search based on spatial relations," in Proc. IEEE Int. Conf. Robot. Autom., 2011, pp. 2818-2824.
36. M. Sridharan, J. Wyatt, and R. Dearden, "Planning to see: A hierarchical approach to planning visual actions on a robot using POMDPs," Artif. Intell., vol. 174, no. 11, pp. 704-725, 2010.
37. D. Nistér and H. Stewénius, "Scalable recognition with a vocabulary tree," in Proc. Comput. Vis. Pattern Recog., 2006, pp. 2161-2168.
38. R. Rusu, "Semantic 3D object maps for everyday manipulation in human living environments," Ph.D. dissertation, Inst. für Informatik, Technische Univ. München, Munich, Germany, 2009.
39. D. Bertsekas and S. Shreve, Stochastic Optimal Control: The Discrete-Time Case. Belmont, MA, USA: Athena Scientific, 2007.