Robotics, Volume 4, Issue 3 (September 2015) – 5 articles , Pages 253-397

Multi-robot foraging has been widely studied in the literature, and the general assumption is that the robots are simple, i.e., with limited processing and carrying capacity. We previously studied continuous foraging with slightly more capable robots, and in this article, we are interested in using similar robots for item delivery. Interestingly, item delivery and foraging are two sides of the same coin: foraging an item from a location is similar to satisfying a demand. We formally define the multi-robot item delivery problem and show that the continuous foraging problem is a special case of it. We contribute distributed multi-robot algorithms that solve the item delivery and foraging problems and describe how our shared world model is synchronized across the multi-robot team. We performed extensive experiments on simulated robots using a Java simulator, and we present our results to demonstrate that we outperform benchmark algorithms from multi-robot foraging. Full article

It is challenging to develop a control algorithm that uses only one sensor to guide an autonomous vehicle. The objective of this research was to develop a control algorithm with a single sensor for an autonomous agricultural vehicle that could identify landmarks in the row-type plantation environment and navigate a vehicle to a point-to-go target location through the plantation. To enable such a navigation system for the plantation system, a laser range finder (LRF) was used as a single sensor to detect objects and navigate a full-size autonomous agricultural tractor. The LRF was used to control the tractor as it followed a path, and landmarks were detected “on-the-go” in real time. The landmarks were selected based on data for their distances calculated by comparison with the surrounding objects. Once the landmarks were selected, a target point was calculated from the landmarks, and the tractor was navigated toward the target. Navigation experiments were successfully conducted on the selected paths without colliding with the surrounding objects. A real time kinematic global positioning system (RTK GPS) was used to compare the positioning between the autonomous control and manual control. The results of this study showed that this control system could navigate the autonomous tractor to follow the paths, and the vehicle position differed from the manually driven paths by 0.264, 0.370 and 0.542 m for the wide, tight, and U-turn paths, respectively, with directional accuracies of 3.139°, 4.394°, and 5.217°, respectively, which are satisfactory for the autonomous operation of tractors on rubber or palm plantations. Therefore, this laser-based landmark detection and navigation system can be adapted to an autonomous navigation system to reduce the vehicle`s sensor cost and improve the accuracy of the positioning. Full article

Multi-robot task allocation (MRTA) is an important area of research in autonomous multi-robot systems. The main problem in MRTA is to allocate a set of tasks to a set of robots so that the tasks can be completed by the robots while ensuring that a certain metric, such as the time required to complete all tasks, or the distance traveled, or the energy expended by the robots is reduced. We consider a scenario where tasks can appear dynamically and a task needs to be performed by multiple robots to be completed. We propose a new algorithm called SQ-MRTA (Spatial Queueing-MRTA) that uses a spatial queue-based model to allocate tasks between robots in a distributed manner. We have implemented the SQ-MRTA algorithm on accurately simulated models of Corobot robots within the Webots simulator for different numbers of robots and tasks and compared its performance with other state-of-the-art MRTA algorithms. Our results show that the SQ-MRTA algorithm is able to scale up with the number of tasks and robots in the environment, and it either outperforms or performs comparably with respect to other distributed MRTA algorithms. Full article

In this paper, we propose a new approach for recognizing intentions of humans by observing their activities with a color plus depth (RGB-D) camera. Activities and goals are modeled as a distributed network of inter-connected nodes in an Activation Spreading Network (ASN). Inspired by a formalism in hierarchical task networks, the structure of the network captures the hierarchical relationship between high-level goals and low-level activities that realize these goals. Our approach can detect intentions before they are realized and it can work in real-time. We also extend the formalism of ASNs to incorporate contextual information into intent recognition. We further augment the ASN formalism with special nodes and synaptic connections to model ordering constraints between actions, in order to represent and handle partial-order plans in our ASN. A fully functioning system is developed for experimental evaluation. We implemented a robotic system that uses our intent recognition to naturally interact with the user. Our ASN based intent recognizer is tested against three different scenarios involving everyday activities performed by a subject, and our results show that the proposed approach is able to detect low-level activities and recognize high-level intentions effectively in real-time. Further analysis shows that contextual and partial-order ASNs are able to discriminate between otherwise ambiguous goals. Full article

Learning and planning are powerful AI methods that exhibit complementary strengths. While planning allows goal-directed actions to be computed when a reliable forward model is known, learning allows such models to be obtained autonomously. In this paper we describe how both methods can be combined using an expressive qualitative knowledge representation. We argue that the crucial step in this integration is to employ a representation based on a well-defined semantics. This article proposes the qualitative spatial logic QSL, a representation that combines qualitative abstraction with linear temporal logic, allowing us to represent relevant information about the learning task, possible actions, and their consequences. Doing so, we empower reasoning processes to enhance learning performance beyond the positive effects of learning in abstract state spaces. Proof-of-concept experiments in two simulation environments show that this approach can help to improve learning-based robotics by quicker convergence and leads to more reliable action planning. Full article