Active Reward Learning for Co-Robotic Vision Based Exploration in Bandwidth Limited Environments
arXiv:2003.05016 · doi:10.1109/ICRA40945.2020.9196922
Abstract
We present a novel POMDP problem formulation for a robot that must autonomously decide where to go to collect new and scientifically relevant images given a limited ability to communicate with its human operator. From this formulation we derive constraints and design principles for the observation model, reward model, and communication strategy of such a robot, exploring techniques to deal with the very high-dimensional observation space and scarcity of relevant training data. We introduce a novel active reward learning strategy based on making queries to help the robot minimize path "regret" online, and evaluate it for suitability in autonomous visual exploration through simulations. We demonstrate that, in some bandwidth-limited environments, this novel regret-based criterion enables the robotic explorer to collect up to 17% more reward per mission than the next-best criterion.
arXiv comment7 pages, 4 figures; accepted for presentation in IEEE Int. Conf. on Robotics and Automation, ICRA '20, Paris, France, June 2020
References in corpus (9)
- Scikit-learn: Machine Learning in Python
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- Unsupervised Deep Feature Extraction for Remote Sensing Image Classification
- A Benchmark and Comparison of Active Learning for Logistic Regression
- Modeling Curiosity in a Mobile Robot for Long-Term Autonomous Exploration and Monitoring
- Information-Guided Robotic Maximum Seek-and-Sample in Partially Observable Continuous Environments
- An Approach to Autonomous Science by Modeling Geological Knowledge in a Bayesian Framework
- Streaming Scene Maps for Co-Robotic Exploration in Bandwidth Limited Environments
- Feature discovery and visualization of robot mission data using convolutional autoencoders and Bayesian nonparametric topic models