Ioan Susnea

Path following, real-time, embedded fuzzy control of a mobile platform wheeled mobile robot

This paper presents a microcontroller implementation of a fuzzy logic control algorithm applied to the mobile platform Pioneer 3-DX. Pioneer 3-DX is a wheeled mobile robot (WMR) with two driving wheels and a caster wheel. The design and implementation of the fuzzy controller is described. Both speed and position are achieved using the same real-time fuzzy controller. The description starts with an example for a circular path following, then presents an implementation of the algorithms for following a generalized curve path.

The bubble rebound obstacle avoidance algorithm for mobile robots

This paper proposes a simple, reactive algorithm for real time obstacle avoidance, aimed to be implemented on low cost, low power microcontrollers. According to this algorithm, the robot reacts to obstacles detected within an area called “sensitivity bubble”, whose shape and size are dynamically adjusted, depending on the kinematics of the robot. Upon detection of an obstacle, the robot “rebounds” in a direction having the lowest density of obstacles, and continues its motion in this direction until the goal becomes visible, or a new obstacle is encountered. Based on experimental results with simulators and real robots, the paper describes the performances and drawbacks of the algorithm, in comparison with other, simple obstacle avoidance algorithms.

Distributed system of mobile platform obstacle avoidance and control as robotic assistant for disabled and elderly

In this paper an experiment aimed to demonstrate that a distributed system of embedded microcontrollers is presented. In the experiment described, didactic mobile robot, People Bot from Mobile Robots has been used, but the entire solution can be easily ported for the implementation of an intelligent wheelchair, capable either to carry an elderly or disabled person, or to move independently in a smart environment, as a sensorial extension of the assisted individual. A number of control modules are located on the mobile robot while others are deployed in an “intelligent environment” can significantly reduce the cost of developing a robotic assistant for the elderly and disabled. The structure of the experimental setup is described in detail, as well as the main algorithms used for each individual task: path following, obstacle avoidance, data acquisition. An obstacle avoidance algorithm, based on ricochet method, named “the bubble rebound algorithm”, is presented, too.

Virtual pheromones to control mobile robots. A neural network approach

This paper introduces the concept of “virtual pheromones” for use in controlling autonomous mobile robots. Virtual pheromones are stored in a map of the environment maintained by a “pheromone server”, which acts like a shared memory for all the agents. Autonomous agents communicate with the pheromone server by means of a radio communication link. A model of the virtual pheromone, which includes spatial diffusion and time decay through evaporation is proposed. The pheromone server can be embodied by a regular computer, a handheld device, or an embedded controller carried by a robot. Indivudual robots, and robotic swarms can be controlled this way. It is emphasized thet the whole system, comprising the pheromone server, the communication system, and the robotic agents act like a neural network. This technique can lead to significant simplification of the task of controlling individual robots and robot swarms.

Wheeled mobile robot control using virtual pheromones and neural networks

This paper presents a novel approach on the implementation of the concept of “virtual pheromones” for use in controlling autonomous mobile robots. Rather than being deployed in the environment, the virtual pheromones are stored in a map of the environment maintained and updated by a “pheromone server”. This map acts like a shared memory for all the agents, by means of a radio communication link between each agent and the pheromone server. No direct communication between agents is required. The pheromone server can be implemented on a regular computer, a handheld device, or an embedded controller carried by a leader robot. The technique described is equally applicable for guiding individual robot and robot swarms. The experiments, performed with mobile robot Pioneer 3-DX show that this method allows significant simplification and cost reduction of the autonomous agents. Several possible applications are discussed.

Obstacle avoidance and path following control of a WMR used as personal robotic assistant

In this paper, an obstacle avoidance method and a fuzzy control, together with a distributed system of embedded microcontrollers, are presented. In the real-time control, a wheeled mobile robot (WMR), Pioneer 3-DX, from Mobile Robots, has been used. The solution adopted can be easily ported for the implementation of an intelligent wheelchair, capable either to carry an elderly or disabled person, or to move independently in a smart environment, as a sensorial extension of the assisted individual. A number of control modules are located on the mobile robot, while others are deployed in an intelligent environment. This solution can significantly reduce the cost of developing a personal robotic assistant (PRA) for the elderly and disabled. The structure of the real-time setup is described in detail, as well as the main algorithms used for each individual task: path following, obstacle avoidance, data acquisition. Also, an obstacle avoidance system, based on ricochet method, named “the bubble rebound method”, is presented.

Improved occupancy-based solutions for energy saving in buildings

In the past decades, despite the huge interest for the topics related to energy conservation and reducing the CO2 emissions, it became obvious that there is an economic reason for the weak progress in these fields: the visible correlation between the economic growth and the energy consumption. As a result, it is very likely that the demand for energy will continue to grow. Since buildings are responsible for 40% of the total energy demand, in this paper we review the vast literature dedicated to energy saving in buildings from the perspective of the feasibility on a large scale. We emphasize the solutions based on detecting and forecasting the building occupancy in order to control the HVAC and lighting systems for energy saving without affecting the comfort of the users. Several improvements of these solutions are proposed.

The Inn at the Crossroads – A Model of Distributed Spatial Knowledge

The paper describes a simple experiment aimed to demonstrate the possibility to create distributed cognitive maps of certain environments by means of recording basic information about the purposeful motion of a population of mobile agents. The environment is assumed to consist in a set of behaviorally significant places interconnected by predefined paths, just like the inns at the crossroads used to be deployed along and across populated areas centuries ago. These active places interact with the mobile agents and create local patches of relevant navigation information, which is shared with other agents that reach the respective place. As a result, the system exhibits a globally consistent spatial behavior, using only locally available, incomplete spatial knowledge. A NetLogo simulation allowed us to compare the average distance traveled by the agents, and the average travel time before reaching their goals, with a similar system wherein the agents walk randomly. As expected, the agents using the distributed spatial knowledge reached their goals much faster than those walking randomly in the same environment. We also explore the possible applications of systems built according to the principles described here.

Emergency Communication System for Fault Diagnosis in Power Distribution Networks

This paper describes a preliminary research aimed to explore the feasibility of the idea of creating an alternative, backup communication system for fault diagnosis in power distribution networks, based on the WSN technology. According to this study, it appears that a plurality of WSN nodes, spatially distributed in a chain topology, and equipped with specially designed communication protocols may route relatively small amounts of data over extended distances. Such a system is, in principle, capable to provide the means for remote fault diagnosis operations in power distribution networks, in circumstances when other communication systems are unavailable.

On Using Passive RFID Tags to Control Robots for Path Following

Although very few robots actually go to Mars, we continue to design these machines as if they were organisms operating in a totally unknown and hostile environment. In fact, in most situations, the environment is not only predictable, but it can also be manipulated so that the missions of the autonomous robot may be supported, by including sensors, actuators, computing and communication equipment. One of the most convenient ways to manipulate the environment is to deploy a number of RFID devices, capable of storing a variety of digital data, aimed to provide autonomous robots with valuable navigation information. As a result, the on-board equipment can be significantly reduced, along with the power requirements, and the overall cost of the robots. While the vast majority of the applications of the RFID technology for robot control are related to robot localization and mapping, this paper presents an experiment aimed to demonstrate the possibility of using RFID tags for path following.