KNOWROB — knowledge processing for autonomous personal robots

Various studies on autonomous robots that perform physical tasks in living environments are being conducted at present to solve the social problems of an aging society with a low birth rate. However, because it remains difficult for all robots to work autonomously in complicated environments, remote control robots may be useful for practical applications. As the purpose of remote control robots is to make direct connections between the operator and user, they may reduce affinity between the robot and the user. In this study, we define autonomous remote control robots with the aspects of both autonomy and remote operation explicitly. Affinity is compared among autonomous remote control robots, remote control robots, and autonomous robots, through controlled experiments on interactions in fetch-and-carry tasks using a domestic mobile manipulator, Human Support Robot, on a test field that is compliant with the World Robot Summit 2020 Rulebook. The results demonstrate that affinity exhibits the following order: autonomous robots, autonomous remote control robots, and remote control robots. Considering that autonomous robots remain under development, autonomous remote control robots may be beneficial for expanding the abilities of physical tasks and social acceptance.

Knowledge processing has patterns which can be found in biological neuron activity and artificial neural networks. The work explores whether an underlying structure exists for knowledge which crosses domains. The results show common data processing patterns in biological systems and human-made knowledge-based systems, present examples of human-generated knowledge processing systems, such as artificial neural networks and research topic knowledge networks, and explore change of system patterns over time. The work analyzes nature-based systems, which are animal connectomes, and observes neuron circuitry of knowledge processing based on complexity of the knowledge processing system. The variety of domains and similarity in processing mechanisms raise the question: if it is common in natural and artificial systems to see this pattern-based knowledge processing, how unique is knowledge processing in humans.

: This paper introduces the principal concepts in the organization and operation of the logic based knowledge processing system called CK-LOG (A Calculus for Knowledge in LOGic) CK-LOG uses the frame based system MDS (the Meta Description System) for knowledge representation and for modelling world states. It uses an inference engine based on Natural Deduction for stating and solving problems. As a knowledge processing system CK-LOG has several capabilities which are new to the technology of knowledge representation systems. CK-LOG has special facilities to represent and reason about actions and their time dependencies. Actions that occur in a world state may create or destroy objects in the world or modify their properties or prevent or support other actions. The effects of actions are described in CK-LOG using modal operators like CREATE, DESTROY, PREVENT, SUPPORT, KEEP, etc. These operator expressions are also used to represent and reason about possible worlds that the actions might lead to. Most significantly, CK-LOG is a logic based knowledge processing system, just as PROLOG is a logic based programming system. CK-LOG uses a three valued logical system with truth values T (true), ?. (unknown) and F (false) to build partial models of world states, and the two valued logical system of T and F in its theorem proving system. The use of the three valued logical system in its models of world states enables CK-LOG to do problem solving in the context of incomplete information about world states.

Autonomous underwater robot control is a very challenging task because of autonomous underwater robot system nonlinearity, time-variance, uncertain external disturbance and difficulty in hydrodynamic modelling. Based on detailed autonomous underwater robot control survey and description of autonomous underwater robot dynamics, in this article we have used a high order sliding modes controller (HOSMC) for depth control of the autonomous underwater robot, based on the third order sliding modes. High order methods allow overcoming the chattering effect by removing the discontinuity of the control vector. We show that these high order controllers hold the properties of classical SM control laws and remove chattering problem. Different simulations have been carried out to show the performance and effectiveness of the proposed method.

Over decades new technologies, algorithms and methods are evolved and proposed. We can witness a paradigm shift from typewriters to computers, mechanics to mechnotronics, physics to aerodynamics, chemistry to computational chemistry and so on. Such advancements are the result of continuing research; which is still a driving force of researchers. In the same way, the research in the field of artificial intelligence (Russell, Stuart & Norvig, 2003) is major thrust area of researchers. Research in AI have coined different concepts like natural language processing, expert systems, software agents, learning, knowledge management, robotics to name a few. The objective of this chapter is to highlight the research path from software agents to robotics. This chapter begins with the introduction of software agents. The chapter further progresses with the discussion on intelligent agent, autonomous agents, autonomous robots, intelligent robots in different sections. The chapter finally concluded with the fine line between intelligent agents and autonomous robots.

<div class=""abs_img""> <img src=""[disp_template_path]/JRM/abst-image/00270004/03.jpg"" width=""300"" /> Autonomous robot “AR Chair”</div> This paper is discusses an autonomous mobile robot entered in the Real World Robotics Challenges 2014 (RWRC) in Tsukuba. Our project was to develop a wheelchair able to navigate stairs autonomously. Step 1 develops a center articulated vehicle, called the AR Chair, which has 4 wheels and a controller including LIDARs. The center articulated vehicle has a stiff structure and travels with the front and rear wheels on the same path, so there is no inner wheels difference. The robotic vehicle carries users weighing up to 100 kg. The autonomous controller is the same as the Smart Dump 7 combined with the RWRC 2013 to achieve the challenge, excluding the geometrical relationship of the steering angle and communication command for motor drivers to the AR Chair. The advantage of the robot is shown by experimental data from the RWRC 2014’s final run. </span>

Planning and scheduling problems have become a promising area of research in the field of artificial intelligence (AI). In order to provide collision avoidance and enable successful completion of the task, the robot requires sophisticated knowledge about the environment for processing the tasks or methods. Knowledge representation and reasoning (KR & R) techniques provide such a level of knowledge to perceive the task environment. These techniques include description logic (DL) and ontology-based approaches. DL provides low-level knowledge to describe an environment. With advances in KR using ontology, high-level knowledge domain descriptions can be obtained more effectively. Knowledge representation techniques aid in temporal, ontological and spatial reasoning in a modeled environment. In this chapter, low-level KR & R techniques for task planning are summarized.

The paper presents an approach to the development of a software environment for creation of intelligent systems. This environment is based on an integrated knowledge representation model that combines both classic knowledge representation means and constraint programming methods with agent-based techniques. In contrast to other systems following constraint programming methods, the environment presented here allows one to manipulate objects with imprecise (subdefinite) values of attributes. The process of refining such subdefinite attributes is performed by means of a special data-driven mechanism. Another feature of the environment is the use of an agent-based technique instead of the traditional production rule technique, in order to increase efficiency of the processes of logical inference and data processing. Due to a natural combination of the data-driven and event-driven mechanisms, the environment can be used for the development of efficient intelli-gent systems for various applications.

The construction of a smart autonomous mobile robot system that can operate in an anonymous environment can be difficult. Building an autonomous mobile robot requires collecting data from sensors and cameras in order to recognize the surrounding environment, get knowledge of existing landmarks, and figure out its position and orientation. Many research studies have been carried out in recent years providing algorithms for achieving autonomous motion of mobile robot systems and object detection. The most common platform utilized for robot motion design is ROS (Robot Operating System) and for object detection YOLO (You Only Look Once) is a common choice. Additionally, the autonomous system needs motion planning in a systematic way to avoid obstacles by using LIDAR or other sensing methods generating the feedback signals required for control of motion around occupied spaces. One of the most effective and versatile feedback systems for mobile robot control can be constructed using visual feedback, which relies on a high-resolution camera that processes the image in real-time and the result is fed back to the control system for decision making. Visual feedback can be employed alone without sensors for feedback control of autonomous mobile robots, and it can be used for multiple tasks like path planning, obstacle avoidance, object detection, object recognition in addition to motion control. In this research, results of design and construction of an autonomous mobile rescue robot for finding victims through video data are presented. It is aimed to find victims via applying video as a data collection and feedback generation tool in the autonomous mobile robot control system. The visual feedback and YOLO v3 are used not only for finding victims but also for motion control. Our autonomous mobile robot is designed to move smoothly to the victim's direction and avoids obstacles by using ROS Global Planner. The robot is tested in multiple scenarios in different locations, various obstacle and victim numbers, and satisfactory results with good performances are obtained.

Knowledge and value: A new perspective on corporate transformation: Solveig Wikstrom and Richard Norman, Routledge (1994), 149 pp., £10.99

Decision making of a vertebrate in response to the sensory signals from the environment is regulated by the neuromodulatory systems in its brain. A vertebrate’s behaviors like focusing attention, cautious risk-aversion and curiosity-seeking exploration are influenced by these neuromodulators. The paper presents an autonomous robotic control approach based on vertebrate neuromodulation and its implementation on multiple open-source hardware platforms. A simple neural network is used to model the neuromodulatory functions for generating context based behavioral responses to sensory signals. The neural network incorporates three types of neurons — attention focusing cholinergic and noradrenergic (ACh/NE), curiosity-seeking dopaminergic (DA), and risk aversive serotonergic (5-HT) neurons. The implementation of the neuronal model on multiple relatively simple autonomous robots is illustrated through the interesting behavior of the robots adapting to changes in the environment. The implementation is done in open-source, open-access robotics software framework of Robot Operating System (ROS).

We propose a robot control system utilizing semantic information behind robot-plans. Robots read the semantic information annotated to control programs, and utilize it for proper situation-recognition and rational action-generation. We try to develop a framework based on reusable and sharable representations among robots and humans. To this end, we construct an ontology of task world defining a systematized vocabulary for task models and knowledge processing. We introduce several important ideas for modeling the task world. We demonstrate an example of execution monitoring in a simulated blocks world task. Semantic information will serve as a guide for rational and reasonable inference, planning, and diagnosis.

Intelligent agents are an important technology, and have many significant applications in wide range of domains. In a goal-driven intelligent agent system, goal is an important concept, where an intelligent agent with a certain goal typically has to satisfy its goal description. In other words, goal matchmaking is one of the major problems in the area of intelligent agent systems. In this paper, we address the problem of matchmaking from a knowledge representation perspective, with a formalization based on description logics (DLs), which is a formal tool of knowledge representation and reasoning. Using effective reasoning capability of description logics (DLs), especially its effective judgment to concept subsumption, we combine the description logics (DLs) and goal reasoning. We also present reasonable algorithms for goal matchmaking based on the devised inferences, and prove that they obey to some commonsense properties. Finally, we report on the implementation of the proposed matchmaking framework, which has been used in migrating workflow systems (MWfM).

Digital twin-based industrial cloud robotics: Framework, control approach and implementation

Fuzzy drive control of an autonomous mobile robot