Search

In this paper we present a novel information-theoretic utility function for selecting actions in a robot-based autonomous exploration task. The robot’s goal in an autonomous exploration task is to create a complete, high-quality map of an unknown environment as quickly as possible. This implicitly requires the robot to maintain an accurate estimate of its pose as it explores both unknown and previously observed terrain in order to correctly incorporate new information into the map. Our utility function simultaneously considers uncertainty in both the robot pose and the map in a novel way and is computed as the difference between the Shannon and the Rényi entropy of the current distribution over maps. Rényi’s entropy is a family of functions parameterized by a scalar, with Shannon’s entropy being the limit as this scalar approaches unity. We link the value of this scalar parameter to the predicted future uncertainty in the robot’s pose after taking an exploratory action. This effectively decreases the expected information gain of the action, with higher uncertainty in the robot’s pose leading to a smaller expected information gain. Our objective function allows the robot to automatically trade off between exploration and exploitation in a way that does not require manually tuning parameter values, a significant advantage over many competing methods that only use Shannon’s definition of entropy. We use simulated experiments to compare the performance of our proposed utility function to these state-of-the-art utility functions. We show that robots that use our proposed utility function generate maps with less uncertainty and fewer visible artifacts and that the robots have less uncertainty in their pose during exploration. Finally, we demonstrate that a real-world robot using our proposed utility function is able to successfully create a high-quality map of an indoor office environment. [ABSTRACT FROM AUTHOR]

Autonomous exploration of motor skills is a key capability of learning robotic systems. Learning motor skills can be formulated as inverse modeling problem, which targets at finding an inverse model that maps desired outcomes in some task space, e.g., via points of a motion, to appropriate actions, e.g., motion control policy parameters. In this paper, autonomous exploration of motor skills is achieved by incrementally learning inverse models starting from an initial demonstration. The algorithm is referred to as skill babbling, features sample-efficient learning, and scales to high-dimensional action spaces. Skill babbling extends ideas of goal-directed exploration, which organizes exploration in the space of goals. The proposed approach provides a modular framework for autonomous skill exploration by separating the learning of the inverse model from the exploration mechanism and a model of achievable targets, i.e. the workspace. The effectiveness of skill babbling is demonstrated for a range of motor tasks comprising the autonomous bootstrapping of inverse kinematics and parameterized motion primitives. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach to modeling curiosity in a mobile robot, which is useful for monitoring and adaptive data collection tasks, especially in the context of long term autonomous missions where pre-programmed missions are likely to have limited utility. We use a realtime topic modeling technique to build a semantic perception model of the environment, using which, we plan a path through the locations in the world with high semantic information content. The life-long learning behavior of the proposed perception model makes it suitable for long-term exploration missions. We validate the approach using simulated exploration experiments using aerial and underwater data, and demonstrate an implementation on the Aqua underwater robot in a variety of scenarios. We find that the proposed exploration paths that are biased towards locations with high topic perplexity, produce better terrain models with high discriminative power. Moreover, we show that the proposed algorithm implemented on Aqua robot is able to do tasks such as coral reef inspection, diver following, and sea floor exploration, without any prior training or preparation. [ABSTRACT FROM AUTHOR]

To date, a large number of algorithms to solve the problem of autonomous exploration and mapping has been presented. However, few efforts have been made to compare these techniques. In this paper, an extensive study of the most important methods for autonomous exploration and mapping of unknown environments is presented. Furthermore, a representative subset of these techniques has been chosen to be analysed. This subset contains methods that differ in the level of multi-robot coordination and in the grade of integration with the simultaneous localization and mapping (SLAM) algorithm. These exploration techniques were tested in simulation and compared using different criteria as exploration time or map quality. The results of this analysis are shown in this paper. The weaknesses and strengths of each strategy have been stated and the most appropriate algorithm for each application has been determined. [ABSTRACT FROM AUTHOR]

We present a technique for mobile robot exploration in unknown indoor environments using only a single forward-facing camera. Rather than processing all the data, the method intermittently examines only small 32×24 downsampled grayscale images. We show that for the task of indoor exploration the visual information is highly redundant, allowing successful navigation even using only a small fraction of the available data. The method keeps the robot centered in the corridor by estimating two state parameters: the orientation within the corridor, and the distance to the end of the corridor. The orientation is determined by combining the results of five complementary measures, while the estimated distance to the end combines the results of three complementary measures. These measures, which are predominantly information-theoretic, are analyzed independently, and the combined system is tested in several unknown corridor buildings exhibiting a wide variety of appearances, showing the sufficiency of low-resolution visual information for mobile robot exploration. Because the algorithm discards such a large percentage of the pixels both spatially and temporally, processing occurs at an average of 1000 frames per second, thus freeing the processor for other concurrent tasks. [ABSTRACT FROM AUTHOR]