This paper presents a software architecture for robots providing manipulation services autonomously in human environments. In an unstructured human environment, a service robot often needs to perform tasks even without human intervention and prior knowledge about tasks and environments. For autonomous execution of tasks, varied processes are necessary such as perceiving environments, representing knowledge, reasoning with the knowledge, and planning for task and motion. While developing each of the processes is important, integrating them into a working system for deployment is also important as a robotic system can bring tangible outcomes when it works in real world. However, such an architecture has been rarely realized in the literature owing to the difficulties of a full integration, deployment, understanding high-level goals without human interventions. In this work, we suggest a software architecture that integrates the components necessary to perform tasks by a real robot without human intervention. We show our architecture composed of deep learning based perception, symbolic reasoning, AI task planning, and geometric motion planning. We implement a deep neural network that produces information about the environment, which are then stored in a knowledge base. We implement a reasoner that processes the knowledge to use the result for task planning. We show our implementation of the symbolic task planner that generates a sequence of motion predicates. We implement an interface that computes geometric information necessary for motion planning to execute the symbolic task plans. We describe the deployment of the architecture through the result of lab tests and a public demonstration. The architecture is developed based on Robot Operating System (ROS) so compatible with any robot that is capable of object manipulation and mobile navigation running in ROS. We deploy the architecture to two different robot platforms to show the compatibility.
Energy accounting is an essential requirement for optimizing energy consumption on mobile devices. State-of-the-art approaches consider application processes and threads as the sole components of energy consumption. In this framework, the energy consumption of system services is unclear and has not been comprehensively studied. In this paper, we suggest that the energy consumption of system services should be investigated to understand the behavior of applications. We propose a fine-grained energy tracing scheme, EnTrack, to enhance the accuracy of energy tracing by identifying and incorporating the energy portions consumed by system services. We implemented EnTrack on the Android platform and validated its functionality and usefulness. In addition, practical usage cases of EnTrack, which uses it as an energy behavior analysis tool, were introduced. The case studies demonstrated that EnTrack enables an understanding of fine-grained energy consumption, especially in system services, which have previously been concealed.
Mobile users are always demanding extended availability in their battery use. Together with enlarged battery capacity, fast charging is one approach that provides an improved user experience in battery use. Recently, device manufacturers have been developing a variety of fast charging techniques for mobile devices. However, the existing techniques severely reduce the charging power when the device is in use while charging. We experimentally demonstrate that the primary cause of the reduction in the charge speed during device use is to cope with the performance degradation incurred by heat generation. We then propose an adaptive charging scheme, called Always-on Quick Charging, which enables fast charging especially when the device is in use. The key idea of our approach is to adjust the charging power while ensuring that the heat generated by the charging does not affect the performance. The proposed scheme is implemented in Google's Pixel 2XL smartphone. The experiment with a real-world usage scenario shows that the charging speed of the proposed scheme is up to 2.4 times faster than the default scheme, while preserving device performance.
Service robots operating in indoor environments should recognize dynamic changes from sensors, such as RGB-depth (RGB-D) cameras, and recall the past context. Therefore, we propose a context query-processing framework, comprising spatio-temporal robotic context query language (ST-RCQL) and a spatio-temporal robotic context query-processing system (ST-RCQP), for service robots. We designed them based on spatio-temporal context ontology. ST-RCQL can query not only the current context knowledge, but also the past. In addition, ST-RCQL includes a variety of time operators and time constants; thus, queries can be written very efficiently. The ST-RCQP is a query-processing system equipped with a perception handler, working memory, and backward reasoner for real-time query-processing. Moreover, ST-RCQP accelerates query-processing speed by building a spatio-temporal index in the working memory, where percepts are stored. Through various qualitative and quantitative experiments, we demonstrate the high efficiency and performance of the proposed context query-processing framework.
Task and motion planning (TAMP) is a key research field for robotic manipulation tasks. The goal of TAMP is to generate motion-feasible task plan automatically. Existing methods for checking motion feasibility of task plan skeletons have some limitations of semantic-free pose candidate sampling, weak search heuristics, and early value commitment. In order to overcome these limitations, we propose a novel constraint satisfaction framework for checking motion feasibility of task plan skeletons. Our framework provides (1) a semantic pose candidate sampling method, (2) novel variable and constraint ordering heuristics based on intra- and inter-action dependencies in a task plan skeleton, and (3) an efficient search strategy using constraint propagation. Based upon these techniques, our framework can improve the efficiency of motion feasibility checking for TAMP. From experiments using the humanoid robot PR2, we show that the motion feasibility checking in our framework is 1.4x to 6.0x faster than previous ones.