Subsumption Architecture Research Articles

A New Action Execution Module for the Learning Intelligent Distribution Agent (LIDA): The Sensory Motor System

This paper presents a cognitive model for an action execution process—the sensory motor system (SMS)—as a new module of the system-level cognitive model for “Learning Intelligent Distribution Agent” (LIDA). Action execution refers to a situation in which a software agent or robot transforms a selected goal-directed action into low-level executable actions and executes them in the real world. A sensorimotor system derived from the subsumption architecture has been implemented into the SMS; several cognitive neuroscience hypotheses have been incorporated as well, including the two visual systems. A computational SMS has been created inside a LIDA-based software agent in Webots to model the execution of a grip action; its simulated results have been verified against human performance. This computational verification by the comparison of model and human behaviors supports the SMS as a qualitatively reasonable cognitive model for action execution. Finally, the SMS has been compared with other alternative models of action execution; this supports the assertion that our new action execution module is applicable across a range of cognitive architectures.

The Pransky interview: Dr Rodney Brooks, Robotics Entrepreneur, Founder and CTO of Rethink Robotics

Purpose – This article, a “Q&A interview” conducted by Joanne Pransky of Industrial Robot Journal, aims to impart the combined technological, business, and personal experience of a prominent, robotic industry engineer-turned entrepreneur regarding the evolution, commercialization, and challenges of bringing a technological invention to market. Design/methodology/approach – The interviewee is Dr Rodney Brooks, the Panasonic Professor of Robotics (emeritus), Massachusetts Institute of Technology (MIT), Computer Science and Artificial Intelligence Lab; Founder, Chief Technical Officer (CTO) and Chairman of Rethink Robotics. Dr Brooks shares some of his underlying principles in technology, academia and business, as well as past and future challenges. Findings – Dr Brooks received degrees in pure mathematics from the Flinders University of South Australia and a PhD in computer science from Stanford University in 1981. He held research positions at Carnegie Mellon University and MIT, and a faculty position at Stanford before joining the faculty of MIT in 1984. He is also a Founder, Board Member and former CTO (1991-2008) of iRobot Corp (Nasdaq: IRBT). Dr Brooks is the former Director (1997-2007) of the MIT Artificial Intelligence Laboratory and then the MIT Computer Science & Artificial Intelligence Laboratory. He founded Rethink Robotics (formerly Heartland Robotics) in 2008. Originality/value – While at MIT, in 1988, Dr Brooks built Genghis, a hexapodal walker, designed for space exploration (which was on display for ten years in the Smithsonian National Air and Space Museum in Washington, D.C.). Genghis was one of the first robots that utilized Brooks’ pioneering subsumption architecture. Dr Brooks’ revolutionary behavior-based approach underlies the autonomous robots of iRobot, which has sold more than 12 million home robots worldwide, and has deployed more than 5,000 defense and security robots; and Rethink Robotics’ Baxter, the world’s first interactive production robot. Dr Brooks has won the Computers and Thought Award at the 1991 International Joint Conference on Artificial Intelligence, the 2008 IEEE Inaba Technical Award for Innovation Leading to Production, the 2014 Robotics Industry Association’s Engelberger Robotics Award for Leadership and the 2015 IEEE Robotics and Automation Award.

Proposed Methodology for Application of Human-like gradual Multi-Agent Q-Learning (HuMAQ) for Multi-robot Exploration

Several attempts have been made by the researchers around the world to develop a number of autonomous exploration techniques for robots. But it has been always an important issue for developing the algorithm for unstructured and unknown environments. Human-like gradual Multi-agent Q-leaming (HuMAQ) is a technique developed for autonomous robotic exploration in unknown (and even unimaginable) environments. It has been successfully implemented in multi-agent single robotic system. HuMAQ uses the concept of Subsumption architecture, a well-known Behaviour-based architecture for prioritizing the agents of the multi-agent system and executes only the most common action out of all the different actions recommended by different agents. Instead of using new state-action table (Q-table) each time, HuMAQ uses the immediate past table for efficient and faster exploration. The proof of learning has also been established both theoretically and practically. HuMAQ has the potential to be used in different and difficult situations as well as applications. The same architecture has been modified to use for multi-robot exploration in an environment. Apart from all other existing agents used in the single robotic system, agents for inter-robot communication and coordination/ co-operation with the other similar robots have been introduced in the present research. Current work uses a series of indigenously developed identical autonomous robotic systems, communicating with each other through ZigBee protocol.

Evolving robot sub-behaviour modules using Gene Expression Programming

Many approaches to AI in robotics use a multi-layered approach to determine levels of behaviour from basic operations to goal-directed behaviour, the most well-known of which is the subsumption architecture. In this paper, the performances of the unigenic Gene Expression Programming (ugGEP) and multigenic GEP (mgGEP) in evolving robot controllers for a wall following robot are analysed. Additionally, the paper introduces Regulatory Multigenic Gene Expression Programming, a new evolutionary technique that can be utilised to automatically evolve modularity in robot behaviour. The proposed technique extends the mgGEP algorithm, by incorporating a regulatory gene as part of the GEP chromosome. The regulatory gene, just as in systems biology, determines which of the genes in the chromosome to express and therefore how the controller solves the problem. In the initial experiments, the proposed algorithm is implemented for a robot wall following problem and the results compared to that of ugGEP and mgGEP. In addition to the wall following behaviour, a robot foraging behaviour is implemented with the aim of investigating whether the position of a specific module (sub-expression tree) in the overall expression tree is of importance when coding for a problem.

Identifying Rhodamine Dye Plume Sources in Near-Shore Oceanic Environments by Integration of Chemical and Visual Sensors

This article presents a strategy for identifying the source location of a chemical plume in near-shore oceanic environments where the plume is developed under the influence of turbulence, tides and waves. This strategy includes two modules: source declaration (or identification) and source verification embedded in a subsumption architecture. Algorithms for source identification are derived from the moth-inspired plume tracing strategies based on a chemical sensor. The in-water test missions, conducted in November 2002 at San Clemente Island (California, USA) in June 2003 in Duck (North Carolina, USA) and in October 2010 at Dalian Bay (China), successfully identified the source locations after autonomous underwater vehicles tracked the rhodamine dye plumes with a significant meander over 100 meters. The objective of the verification module is to verify the declared plume source using a visual sensor. Because images taken in near shore oceanic environments are very vague and colors in the images are not well-defined, we adopt a fuzzy color extractor to segment the color components and recognize the chemical plume and its source by measuring color similarity. The source verification module is tested by images taken during the CPT missions.

A Subsumption Architecture to Develop Dynamic Cognitive Network-Based Models With Autonomous Navigation Application

This work proposes an original approach based on subsumption architecture to build dynamic cognitive networks (DCN). Dynamic cognitive network is a soft computing technique similar to fuzzy cognitive maps (FCM) which are able to easily model cause–effect behaviors. FCMs have been applied in several areas of knowledge; however, they present some restrictions for modeling dynamic systems, specifically temporal dependencies among events. Due to these restrictions, alternative approaches based on FCM and also fuzzy networks have appeared in the literature. Dynamic cognitive networks are one of these techniques. Hence, this study presents a new type of DCN which incorporates different types of concepts and causal relations able to circumvent the main drawbacks of FCM modeling. The new approach is based on the subsumption architecture, which allows to represent, model, and implement several behaviors of a dynamic systems through a composition of hierarchical DCNs. An application of the new DCN technique in autonomous navigation is also developed in order to validate the approach.

Multiple mobile robots system with network-based subsumption architecture

In this paper, a unique multiple mobile robots system is proposed to enable engineering students and engineers in the field to efficiently learn subsumption architecture and develop swarm intelligence. The subsumption architecture is known as one of the behaviour-based artificial intelligence. Each of multiple mobile robots within the system has three wheels driven by DC motors and six position sensitive detector (PSD) sensors. Network-based subsumption architecture is considered to realise a schooling behaviour by using only information from the PSD sensors. Further, a server supervisory control is introduced for poor hardware platforms with limitations of software development, i.e., the mobile robots can only behave based on the most simply subdivided reaction behaviours, i.e., reflex actions, generated from agents. Experimental results show interesting behaviour among the multiple mobile robots, such as following, avoidance and schooling.

A proposal of experimental education system of mechatronics

Recently, many studies on educational system are being conducted. In this manuscript, a unique education system is proposed for mechanical engineers to be able to efficiently learn basic mechatronics techniques. The system is composed of three subsystems. The first subsystem is used to learn input/output port operations, periodically LED lights ON/OFF and a stepping motor control. The second subsystem is effective to learn AD transformation for several sensor information, DA transformation for DC motor control and a PID control method. Further, the third subsystem is multiple mobile robots system to learn the subsumption architecture for schooling behavior. The effectiveness of the proposed systems was confirmed through experimental instructions in Tokyo University of Science, Yamaguchi.

Behaviors Coordination and Learning on Autonomous Navigation of Physical Robot

B ehaviors coordination is one of keypoints in behavior based robotics. Subsumption architecture and motor schema are example of their methods. In order to study their characteristics, experiments in physical robot are needed to be done. It can be concluded from experiment result that the first method gives quick, robust but non smooth response . Meanwhile the latter gives slower but smoother response and it is tending to reach target faster. Learning behavior improve robot’s performance in handling uncertainty. Q learning is popular reinforcement learning method that has been used in robot learning because it is simple, convergent and off policy. The learning rate of Q affects robot’s performance in learning phase. Q learning algorithm is implemented in subsumption architecture of physical robot. As the result, robot succeeds to do autonomous navigation task although it has some limitations in relation with sensor placement and characteristic.

Practical Education Curriculum for Autonomous Mobile Robot (Project Learning Program for School Based on Subsumption Architecture)

There are presently no robots around us in our society if we define a robot as an autonomous machine working in the arena of offices, homes, disaster sites, etc., not in factories. Mechatronics, dynamics, and robotics involving humans are a world of strong nonlinearity. This paper investigates the approach to the emergence of the target behavior of an autonomous mobile robot by learning with Subsumption Architecture (SA) to break through the problems of the conventional robotics with the SMPA (Sense-Model-Plan-Act) framework in the real world. It has showed the way things are learned in the real world with SA and has been developed into a practical curriculum for education as an introduction to robotics that has an intellectual and emotional appeal.

Evolving a metabolic subsumption architecture for cooperative control of the e-puck

Subsumption architectures are a well-known model for behaviour-based robotic control. The global behaviour is achieved by defining a hierarchy of increasingly sophisticated behaviours. We are interested in using evolutionary algorithms to develop appropriate control architectures. We observe that the layered arrangement of behaviours in subsumption architectures are a significant obstacle to automating the development of control systems. We propose an alternative subsumption architecture inspired by the bacterial metabolism, that is more amenable to evolutionary development, in which communities of simple reactive agents combine in a stochastic process to confer appropriate behaviour on the robot. We evaluate this approach by developing a traditional and a metabolic solution to a simple control problem using a simulation of the e-puck educational robot. Additionally we show that behavioural strategies designed into the metabolic controller can also be optimised through artificial evolution.

Cooperative swarm control for multiple mobile robots using only information from PSD sensors

Recently, many studies on swarm robotics have been conducted in which the aim seems to be the realization of an ability to perform complex tasks by cooperating with each other. Future progress and concrete applications are expected. The objective of this study was to construct a cooperative swarm system by using multiple mobile robots. First, multiple mobile robots with six position-sensitive detector (PSD) sensors were designed. A PSD sensor is a type of photo sensor. A control system was considered to realize swarm behavior, such as that shown by Ligia exotica, by using only information from the PSD sensors. Experimental results showed interesting behavior among the multiple mobile robots, such as following, avoidance, and schooling. The controller of the schooling mode was designed based on subsumption architecture. The proposed system was demonstrated to high school students at OPEN CAMPUS 2010, held in Tokyo University of Science, Yamaguchi.

BehaviorShop: An Intuitive Interface for Interactive Character Design

Artificial intelligence for interactive characters is held back by the difficulty of actually creating those characters. There is a need for intuitive tools which simplify the process of building complex AI characters. In this paper, we present BehaviorShop, a tool for building interactive characters, and the results of a study to test the effectiveness and ease of use of this tool. The majority (80%) of test subjects were able to successfully create a complex character using BehaviorShop. Our results show success with this interface, and the advantage of using the subsumption architecture as a paradigm for character creation.

EXTENDING FEYNMAN'S FORMALISMS FOR MODELING HUMAN JOINT ACTION COORDINATION

The recently developed Life-Space-Foam approach to goal-directed human action deals with individual actor dynamics. This paper applies the model to characterize the dynamics of co-action by two or more actors. This dynamics is modelled by (i) a two-term joint action (including cognitive/motivatonal potential and kinetic energy), and (ii) its associated adaptive path integral, representing an infinite-dimensional neural network. Its feedback adaptation loop has been derived from Bernstein's concepts of sensory corrections loop in human motor control and Brooks' subsumption architectures in robotics. Potential applications of the proposed model in human-robot interaction research are discussed.

Behavior-based coverage optimization approach in wireless sensor network

For hybrid wireless sensor networks with mobile nodes,to optimize the coverage performance,based on the subsumption architecture,a kind of behavior-based control strategy for mobile nodes was proposed.Five basic behaviors were designed,i.e.,Stop,Wander,Avoid_Static_Node,Avoid_Mobile_Node and Move_To_Coverage_Hole.And the competition and suppression mechanism for choice of behavior were used.Simulation results show the validity of the algorithm.

Integrated cognitive architectures: a survey

This article aims to present an account of the state of the art research in the field of integrated cognitive architectures by providing a review of six cognitive architectures, namely Soar, ACT-R, ICARUS, BDI, the subsumption architecture and CLARION. We conduct a detailed functional comparison by looking at a wide range of cognitive components, including perception, memory, goal representation, planning, problem solving, reasoning, learning, and relevance to neurobiology. In addition, we study the range of benchmarks and applications that these architectures have been applied to. Although no single cognitive architecture has provided a full solution with the level of human intelligence, important design principles have emerged, pointing to promising directions towards generic and scalable architectures with close analogy to human brains.

Decision Making for a Mobile Robot Using Potential Function

We discuss decision making for a behavior-based robot with modules which determining robot action. The subsumption architecture (SA) arranges modules in layers, giving upper-layer module action priority over lower-layer modules. Although implementation is easy, results in many inefficient actions because upper-layer module are used regardless of other modules. We solve this problem by representing actions by Potential Function (PF), in which maximum votes are collected from modules. Using event-driven state transition, the robot decides its action with appropriate sets of modules changed based on the situation. We apply this to navigation tasks in a corridor and show simulation results. When we give a map and path designation to the robot, we use a handwriting map interface. We compare object-oriented design SA and PMF with our proposal and show how inefficient actions are reduced using our proposal.

EMULATION OF HUMAN FEELINGS AND BEHAVIORS IN AN ANIMATED ARTWORK

The behavior of an animated artwork, survivor — a classroom chair which walks, with a dynamics which some viewers find haunting — reflects an attempt to emulate (and suggest to viewers) some feelings and behaviors that are typical of survivors of landmine blasts, learning to use crutches. The artwork itself is intended for sensitizing viewers to the horror experienced by those who survive, and those who do not. The behavior of such a survivor is affected by several factors: some are due to the objective difficulty of using prosthetic legs, and some are due to emotional factors, e.g., fear, "shame" of being in such situation, and pain. The mechanical structure, strongly conditioned by artistic requirements, was combined with a control system that exhibits appropriate behaviors. Behavioral control, a technique developed for the control of mobile robots, was used in survivor, and implemented over a modified version of the traditional Brooks' subsumption architecture. This technique makes it possible to emulate normal locomotion behaviors such as the need of avoiding obstacles and typical animal feelings such as curiosity, hunger, fatigue and fear. We describe the mechanics and viewers' response, and formalize aesthetic response. We briefly survey computer modelling of emotions, robotic art, and biomimetic locomotion in robotics.

Real-Time Motion Planning for a Volleyball Robot Task Based on a Multi-Agent Technique

This paper takes the volleyball robot task as an example of a dynamic manipulation task and presents a multi-agent-based motion-planning framework for it. Each subtask in the motion planning is defined as an agent. The motion planning is accomplished by the solution of each agent activated by a blackboard. It is convenient to extend the module and enable real-time control compared to the hierarchy and subsumption architecture. In the solution of each subtask, one difference from the motion planning of other ball-playing robots is that simple fuzzy rules are adopted to determine the hitting position, which leads to smaller hitting velocities beneficial for task control. The other difference is that the task-based directional manipulability measure (TDMM) is used to optimize the robot configuration on the basis of optimal hitting path, so as to improve the manipulating ability on task direction. The simulation of a planar three-link manipulator ball-hitting task is implemented by the MATLAB/Simulink tool. The virtual target of the hitting motion is validated on the ABB manipulator by the ball-catching experiment.

Generation of Adapting Behavior by Multi-Robot using Parameter Searching on Subsumption Architecture

In this research, we proposed multi-robot system that has robustness to the change of environments and has adaptability to the change of tasks and number of robots. To implement them, we use parameter learning on subsumption architecture.The subsumption architecture control robots' fundamental behaviors and robots move continuously in principle.The optimal value of the parameter and the number of robot that does the task in field are searched by learning. As the result,the robot's action on the task is improved (updated).Proposed system has functions to recognize the task and to generate the recordation memory.And then robots adapt to the change of tasks and the number of robots.In this paper, the function of proposed system is tested in simulation experiments.