Abstract
For robots navigating in unknown environments, naïvely following the shortest path toward the goal often leads to poor visibility of free space, limiting navigation speed, or even preventing forward progress altogether. In this work, we train a guidance function to give the robot greater visibility into unknown parts of the environment. Unlike exploration techniques that aim to observe as much map as possible for its own sake, we reason about the value of future observations directly in terms of expected cost-to-goal. We show significant improvements in navigation speed and success rate for narrow field-of-view sensors such as popular RGBD cameras. However, contrary to our expectations, we show that our strategy makes little difference for sensors with fields-of-view greater than 80\(^{\circ }\), and we discuss why the naïve strategy is hard to beat.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Following the POMDP problem formulation developed in [9], this true optimal expected cost would be defined as \(h^*(b_t,a_t) = \sum _{s_{t+1}}P(s_{t+1}|b_t,a_t)V^*(s_{t+1})\). We omit a detailed discussion of the POMDP formulation of this problem for brevity, but note that it provides the basis for our mathematical approach and approximations.
References
Arora, S., et al.: Emergency maneuver library-ensuring safe navigation in partially known environments. In Proceedings of the ICRA (2015)
Bachrach, A., et al.: RANGE - robust autonomous navigation in GPS-denied environments. J. Field Rob. 28(5), 644–666 (2011)
Bekris, K.E., Kavraki, L.E.: Greedy but safe replanning under kinodynamic constraints. In: Proceedings of the ICRA (2007)
Fraichard, T., Asama, H.: Inevitable collision states-a step toward safer robots? Adv. Rob. 18(10), 1001–1024 (2004)
Kaelbling, L.P., et al.: Planning and acting in partially observable stochastic domains. Artif. Intell. 101(1), 99–134 (1998)
Kurniawati, H., et al.: SARSOP: Efficient point-based POMDP planning by approximating optimally reachable belief spaces. In: Proceedings of the RSS (2008)
Likhachev, M., Stentz, A.: PCPP: Efficient probabilistic planning with clear preferences in partially-known environments. In: Proceedings of the AAAI (2006)
Makarenko, A.A., et al.: An experiment in integrated exploration. In: Proceedings of the IROS (2002)
Richter, C., et al.: Bayesian learning for high-speed navigation in unknown environments. In: Proceedings of the ISRR (2015)
C. Richter et al. Markov chain hallway and Poisson forest environment generating distributions. Technical Report MIT-CSAIL-TR-2015-014 (2015)
Schouwenaars, T., et al.: Receding horizon path planning with implicit safety guarantees. In: Proceedings of the ACC (2004)
Simmons, R., Koenig, S.: Probabilistic robot navigation in partially observable environments. In: Proceedings of the IJCAI (1995)
Stachniss, C., et al.: Information gain-based exploration using Rao-Blackwellized particle filters. In: Proceedings of the RSS (2005)
Watterson, M., Kumar, V.: Safe receding horizon control for aggressive MAV flight with limited range sensing. In: Proceedings of the IROS (2015)
Yamauchi, B.: A frontier-based approach for autonomous exploration. In: Proceedings of the Computational Intelligence in Robotics and Automation (1997)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Richter, C., Roy, N. (2017). Learning to Plan for Visibility in Navigation of Unknown Environments. In: Kulić, D., Nakamura, Y., Khatib, O., Venture, G. (eds) 2016 International Symposium on Experimental Robotics. ISER 2016. Springer Proceedings in Advanced Robotics, vol 1. Springer, Cham. https://doi.org/10.1007/978-3-319-50115-4_34
Download citation
DOI: https://doi.org/10.1007/978-3-319-50115-4_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-50114-7
Online ISBN: 978-3-319-50115-4
eBook Packages: EngineeringEngineering (R0)