High Performance Outdoor Navigation from Overhead Data using Imitation Learning

By David Silver, J. Bagnell, Anthony Stentz. 2008

80 citations recorded by the source corpus.

High performance, long-distance autonomous navigation is a central problem for field robotics. Efficient navigation relies not only upon intelligent onboard systems for perception and planning, but also the effective use of prior maps and knowledge. While the availability and quality of low cost, high resolution satellite and aerial terrain data continues to rapidly improve, automated interpretation appropriate for robot planning and navigation remains difficult. Recently, a class of machine learning techniques have been developed that rely upon expert human demonstration to develop a function mapping overhead data to traversal cost. These algorithms choose the cost function so that planner behavior mimics an expert's demonstration as closely as possible. In this work, we extend these methods to automate interpretation of overhead data. We address key challenges, including interpolation-based planners, non-linear approximation techniques, and imperfect expert demonstration, necessary to apply these methods for learning to search for effective terrain interpretations. We validate our approach on a large scale outdoor robot during over 300 kilometers of autonomous traversal through complex natural environments.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Reinforcement learning in robotics: A survey (2013, methodology): “These techniques, and many variants, have been recently successfully applied to outdoor robot navigation (Ratliff et al., 2006a; Silver et al., 2008, 2010), manipulation (Ratliff et al., 2007), and quadruped locomotion (Ratliff et al., 2006a, 2007; Kolter et al., 2007).”
Learning to search: Functional gradient techniques for imitation learning (2009, methodology): “This effect can be counteracted with a small modification to the procedure of approximating the functional gradient proposed in (Silver et al., 2008)9.”
Active learning from demonstration for robust autonomous navigation (2012, unknown): “Validation Cost Ratio (b) Random Subsets Fig.”
A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress (2018, methodology): “further, Shiarlis et al. [50] performs IRL with some demonstrations that fail to even complete the task. Figure 8: Learning with a perturbed demonstration in an unstructured terrain. Figure reprinted [26] with permission from MIT press. An expert provides three demonstration trajectories - red, blue”
Contextual classification with functional Max-Margin Markov Networks (2009, background): “puts for footstep and grasp planning [18] and path planning [22].”
Imitation Learning (2017, background): “These include ﬂying vehicles [Sammut et al. 2014; Abbeel et al. 2007; Ng et al. 2006] and ground vehicles [Silver et al. 2008; Ratliff et al. 2007; Chernova and Veloso 2007a; Ollis et al. 2007].”
Reinforcement Planning: RL for optimal planners (2012, methodology): “Consider an unmanned ground vehicle (UGV) system similar to that discussed in [5].”
A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning (2010, methodology): “…are used to learn a controller, have proven very useful in practice and have led to state-of-the art performance in a variety of applications (Schaal, 1999; Abbeel and Ng, 2004; Ratliff et al., 2006; Silver et al., 2008; Argall et al., 2009; Chernova and Veloso, 2009; Ross and Bagnell, 2010).”