Break on through: Tunnel-based exploration to learn about outdoor terrain
نویسندگان
چکیده
We study the problem of designing a ground robot that learns how to navigate in natural, outdoor settings. This robot must learn, through its own experience, a traversability model. This model provides a mapping from the robot’s sensors to a traversability measure. We propose a novel approach to exploration in which the robot purposefully probes into apparent obstacles, with the goal of improving its traversability model. We formulate a decision-theoretic algorithm that identifies potential “tunnels” through apparent obstacles and estimates the benefit of exploring them. We have implemented and tested the algorithm on an outdoor robot platform and we present results from initial experiments that demonstrate the operation of our algorithm and quantify its performance advantage over a baseline system.
منابع مشابه
Self-Supervised Terrain Classification for Planetary Surface
Exploration Rovers 2 3 4 Christopher A. Brooks, Karl Iagnemma 5 Department of Mechanical Engineering 6 Massachusetts Institute of Technology 7 Cambridge, MA 02139 8 [email protected], [email protected] 9 10 Abstract 11 12 For future planetary exploration missions, improvements in autonomous rover 13 mobility have the potential to increase scientific data return by providing safe 14 access to geol...
متن کاملComparison of Different Approaches to Vibration-based Terrain Classification
There is a variety of different terrain types in outdoor environments, each posing different dangers to the robot and demanding a different driving style. In a previous paper, we presented a terrain classification method based on Support Vector Machines (SVM), which uses vibrations induced in the body of the robot to learn different terrain classes. However, in the previous paper, our experimen...
متن کاملSVMs for Vibration-Based Terrain Classification
When an outdoor mobile robot traverses different types of ground surfaces, different types of vibrations are induced in the body of the robot. These vibrations can be used to learn a discrimination between different surfaces and to classify the current terrain. Recently, we presented a method that uses Support Vector Machines for classification, and we showed results on data collected with a ha...
متن کاملEstimation of groundwater inflow situation using fuzzy logic: a case study (Beheshtabad water conveying tunnel, Iran)
Water inflow is one of the most important challenges in the underground excavations. In addition to inducing working conditions and environmental problems, it decreases the stability and quality of the surrounding rocks. The direct method of measuring rock mass hydraulic conductivity consists of drilling the boreholes and observing the rate of fluid lost in the boreholes. Applying this method i...
متن کاملSafe Exploration in Markov Decision Processes
In environments with uncertain dynamics exploration is necessary to learn how to perform well. Existing reinforcement learning algorithms provide strong exploration guarantees, but they tend to rely on an ergodicity assumption. The essence of ergodicity is that any state is eventually reachable from any other state by following a suitable policy. This assumption allows for exploration algorithm...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2008