Exploration Of Unstructured Environments Research Articles

A Semi-Supervised Reservoir Computing System Based on Tapered Whisker for Mobile Robot Terrain Identification and Roughness Estimation

Identifying terrain type is important for safely operating robots exploration in unstructured environments. In this letter, we firstly proposed a novel tapered whisker-based semi-supervised reservoir computing (TWSSRC) system for improving terrain classification and terrain property estimation for traversability assessment with low computing cost. Three Hall sensors are used to capture the vibration at different locations of the tapered whisker. It could provide morphological computation power to achieve frequency separation in the time domain simultaneously without any data procession and only with the help of an additional simple linear regression, different signals can be classified. The movement of the robot on different types of terrain will result in different vibration behaviors of the whiskers and the whiskered robot can learn from prior physical experiences through cost-efficient self-supervised reservoir computing to achieve auto-labeling of new terrain and terrain classification. Experimental results demonstrate that this method can achieve good performance when the robot encounters new terrain and can accurately estimate the property of the unknown terrain surface at different robot speeds.

A Deep Reinforcement Learning Strategy Combining Expert Experience Guidance for a Fruit-Picking Manipulator

When using deep reinforcement learning algorithms for path planning of a multi-DOF fruit-picking manipulator in unstructured environments, it is much too difficult for the multi-DOF manipulator to obtain high-value samples at the beginning of training, resulting in low learning and convergence efficiency. Aiming to reduce the inefficient exploration in unstructured environments, a reinforcement learning strategy combining expert experience guidance was first proposed in this paper. The ratios of expert experience to newly generated samples and the frequency of return visits to expert experience were studied by the simulation experiments. Some conclusions were that the ratio of expert experience, which declined from 0.45 to 0.35, was more effective in improving learning efficiency of the model than the constant ratio. Compared to an expert experience ratio of 0.35, the success rate increased by 1.26%, and compared to an expert experience ratio of 0.45, the success rate increased by 20.37%. The highest success rate was achieved when the frequency of return visits was 15 in 50 episodes, an improvement of 31.77%. The results showed that the proposed method can effectively improve the model performance and enhance the learning efficiency at the beginning of training in unstructured environments. This training method has implications for the training process of reinforcement learning in other domains.

Design of a Robotic Module for Autonomous Exploration and Multimode Locomotion

The mechanical design of a novel robotic module for a self-reconfigurable modular robotic system is presented in this paper. The robotic module, named Scout robot, was designed to serve both as a fully sensorized autonomous miniaturized robot for exploration in unstructured environments and as a module of a larger robotic organism. The Scout robot has a quasi-cubic shape of 105 mm × 105 mm × 123.5 mm, and weighs less than 1 kg. It is provided with tracks for 2-D locomotion and with two rotational DoFs for reconfiguration and macrolocomotion when assembled in a modular structure. A laser sensor was incorporated to measure the distance and relative angle to an object, and image-guided locomotion was successfully demonstrated. In addition, five Scout robot prototypes were fabricated, and multimodal locomotion of assembled robots was demonstrated.

Percolation enhanced prioritised multi-robot exploration of unstructured environments

Continuous and rapid coverage of the unstructured disaster areas in search of possible survivors is a time critical operation where prior information about the environment is not available or very limited. Human navigation of such areas is definitely not feasible due to the nature of the debris. Localisation of possible survivors necessitates the uninterrupted navigation of robotic aiding devices within the rubble without getting trapped into dead ends. This paper introduces firstly a goal-oriented exploration approach where prior information about possible survivors' location information may be found. Whenever prior information is not available, the system is further extended as a second novel methodology to a prioritised exploration, guided by a percolation inspired finite state automaton that gives priority to navigation through connected voids. The evaluation of the proposed methodologies is done for different simulation scenarios with different number of robots cooperatively carrying the exploration task.

A novel low-cost, limited-resource approach to autonomous multi-robot exploration and mapping

Mobile robots are becoming more heavily used in environments where human involvement is limited, impossible, or dangerous. These robots perform some of the more laborious human tasks on Earth and throughout the solar system, simultaneously saving resources and offering automation. Higher levels of autonomy are also being sought in these applications, such as distributed exploration and mapping of unknown areas. Smaller, less expensive mobile robots are becoming more prevalent, which introduces unique challenges in terms of limited sensing accuracy and onboard computing resources. This paper presents a novel low-cost, limited-resource approach to autonomous multi-robot mapping and exploration in unstructured environments. Design and implementation details are presented, along with results from two planetary style environments. Results demonstrate that low-cost ($ 1250) mobile robots capable of simultaneous localization and mapping can be successfully constructed. The multi-robot system presented in this paper participated in the 2008 International Conference on Robotics and Automation (ICRA) Space Robotics Challenge, receiving two awards for successfully completing the ’Onto the Surface’ and ’Map the Environment’ events in a simulated planetary environment. This work demonstrates not only that such systems are possible, but also that this direction of research is important and needs attention.

A Novel Teleoperated Hybrid Wheel-Limb Hexapod for Lunar Craters' Exploration

Successful robotic planetary exploration missions are not without technical and scientific challenges. Appropriate control and mobility of the robot is critical for successful exploration in unstructured environments. We address these problems through an overview of an under development telerobotic platform for exploration missions to the lunar craters. The platform is based on a novel transforming hybrid walking/roving Lunar Exploration Omnidirectional Netbot (LEON). We describe a versatile dynamic engine based simulator/teleoperation platform called ERode (Eric Rohmer Open Dynamic Engine), which allows developing, simulating and teleoperation of LEON. We also introduce the novel hybrid wheel/limb design of LEON, whereby two of its six limbs fold into themselves transforming into wheels. This possibility of transformation results in increased mobility in the environment, by adapting to different soil conditions. Furthermore, this system has a limited bulkiness compared to hybrid systems owning both wheels and legs, and it has an increased wheel diameter compared to hybrid systems having wheels at the tip of their legs. Preliminary experimental or simulated results are also presented, showing the performance of the hybrid system dealing with different types of terrain.