Learning Context-Based Outcomes for Mobile Robots in Unstructured Indoor Environments

We present a method to learn context-dependent outcomes of behaviors in unstructured indoor environments. The idea is that certain features in the environment may be predictive of differences in outcomes, such as how long a mobile robot takes to traverse a corridor. Doing so enables the robot to plan more effectively, and also be able to interact with people more effectively by more accurately predicting when its plans may take longer to execute or may be likely to fail. We use a node-and-edge based map of the environment and treat the traversal time of the robot for each edge as a random variable to be characterized. The first step is to determine whether the distribution of the random variable is multimodal and, if so, we learn to classify the modes using a hierarchy of plan-time features (e.g., time of the day, day of the week) and run-time features (observations of recent traversal times through other corridors). We utilize a cascading regression system that first estimates which mode of the traversal distribution we expect the robot to observe, and then predict the actual traversal time through a corridor. On average, our method produces a mean residual error of less than 2.7 seconds.

[1]  Wolfram Burgard,et al.  Adapting navigation strategies using motions patterns of people , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[2]  Stephanie Rosenthal,et al.  An effective personal mobile robot agent through symbiotic human-robot interaction , 2010, AAMAS.

[3]  Rory A. Cooper,et al.  Spectral Machine Learning for Predicting Power Wheelchair Exercise Compliance , 2014, ISMIS.

[4]  Friedrich M. Wahl,et al.  Acquisition of statistical motion patterns in dynamic environments and their application to mobile robot motion planning , 1997, Proceedings of the 1997 IEEE/RSJ International Conference on Intelligent Robot and Systems. Innovative Robotics for Real-World Applications. IROS '97.

[5]  Manuela M. Veloso,et al.  WiFi localization and navigation for autonomous indoor mobile robots , 2010, 2010 IEEE International Conference on Robotics and Automation.

[6]  Stephanie Rosenthal,et al.  Using Decision-Theoretic Experience Sampling to Build Personalized Mobile Phone Interruption Models , 2011, Pervasive.

[7]  Ronald C. Arkin,et al.  An Behavior-based Robotics , 1998 .

[8]  Karen Zita Haigh,et al.  Learning situation-dependent costs: improving planning from probabilistic robot execution , 1998, AGENTS '98.

[9]  Reid G. Simmons,et al.  Smartphone Interruptibility Using Density-Weighted Uncertainty Sampling with Reinforcement Learning , 2011, 2011 10th International Conference on Machine Learning and Applications and Workshops.

[10]  Gamini Dissanayake,et al.  Robot path planning in a social context , 2010, 2010 IEEE Conference on Robotics, Automation and Mechatronics.

[11]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..