Reactive Robot Navigation

Many animals meander in environments and avoid collisions. How the underlying neuronal machinery can yield robust behaviour in a variety of environments remains unclear. In the fly brain, motion-sensitive neurons indicate the presence of nearby objects and directional cues are integrated within an area known as the central complex. Such neuronal machinery, in contrast with the traditional stream-based approach to signal processing, uses an event-based approach, with events occurring when changes are sensed by the animal. Contrary to classical von Neumann computing architectures, event-based neuromorphic hardware is designed to process information asynchronously and in a distributed manner. Inspired by the fly brain, we model, for the first time, a neuromorphic closed-loop system mimicking essential behaviours observed in flying insects, such as meandering in clutter and crossing of gaps, both of which are also highly relevant for autonomous vehicles. We implemented our system both i...

In this paper, we present a new method for vision-based, reactive robot navigation that enables a robot to move in the middle of the free space by exploiting both central and peripheral vision. The robot employs a forward-looking camera for central vision and two side-looking cameras for sensing the periphery of its visual field. The developed method combines the information acquired by this trinocular vision system and produces low-level motor commands that keep the robot in the middle of the free space. The approach follows the purposive vision paradigm in the sense that vision is not studied in isolation but in the context of the behaviors that the system is engaged as well as the environment and the robot's motor capabilities. It is demonstrated that by taking into account these issues, vision processing can be drastically simplified, still giving rise to quite complex behaviors. The proposed method does not make strict assumptions about the environment, requires very low level information to be extracted from the images, produces a robust robot behavior and is computationally efficient. Results obtained by both simulations and from a prototype on-line implementation demonstrate the effectiveness of the method.

In this paper, we present a new method for vision-based, reactive robot navigation that enables a robot to move in the middle of the free space by exploiting both central and peripheral vision. The system employs a forward-looking camera for central vision and two side-looking cameras for sensing the periphery of the robot's visual field. The developed method combines the information acquired by this trinocular vision system and produces low-level motor commands that keep the robot in the middle of the free space. The approach ...

The variety of neural models and robotic hardware has made simulation writing time-consuming and error prone, forcing thus scientists to spend a substantial amount of time on the implementation of their models. We developed a framework called "Robby" that allows the quick simulation of large-scale neural networks designed for robotic control by spiking neural networks. It provides both mechanism for robotic communication and tools for building and simulating neural controllers. We present the basic building blocks of "Robby" and a simple experiment to show its practical value.

In this paper we try to develop an algorithm for visual obstacle avoidance of autonomous mobile robot. The input of the algorithm is an image sequence grabbed by an embedded camera on the B21r robot in motion. Then, the optical flow information is extracted from the image sequence in order to be used in the navigation algorithm. The optical flow provides very important information about the robot environment, like: the obstacles disposition, the robot heading, the time to collision and the depth. The strategy consists in balancing the amount of left and right side flow to avoid obstacles, this technique allows robot navigation without any collision with obstacles. The robustness of the algorithm will be showed by some examples.

In this paper we try to develop an algorithm for visual obstacle avoidance of autonomous mobile robot. The input of the algorithm is an image sequence grabbed by an embedded camera on the B21r robot in motion. Then, the optical flow information is extracted from the image sequence in order to be used in the navigation algorithm. The optical flow provides very important information about the robot environment, like: the obstacles disposition, the robot heading, the time to collision and the depth. The strategy consists in balancing the amount of left and right side flow to avoid obstacles, this technique allows robot navigation without any collision with obstacles. The robustness of the algorithm will be showed by some examples.

Understanding why deep neural networks and machine learning algorithms act as they do is a difficult endeavor. Neuroscientists are faced with similar problems. One way biologists address this issue is by closely observing behavior while recording neurons or manipulating brain circuits. This has been called neuroethology. In a similar way, neurorobotics can be used to explain how neural network activity leads to behavior. In real world settings, neurorobots have been shown to perform behaviors analogous to animals. Moreover, a neuroroboticist has total control over the network, and by analyzing different neural groups or studying the effect of network perturbations (e.g., simulated lesions), they may be able to explain how the robot's behavior arises from artificial brain activity. In this paper, we review neurorobot experiments by focusing on how the robot's behavior leads to a qualitative and quantitative explanation of neural activity, and vice versa, that is, how neural activity leads to behavior. We suggest that using neurorobots as a form of computational neuroethology can be a powerful methodology for understanding neuroscience, as well as for artificial intelligence and machine learning.

Humans and other terrestrial animals use vision to traverse novel cluttered environments with apparent ease. On one hand, although much is known about the behavioral dynamics of steering in humans, it remains unclear how relevant perceptual variables might be represented in the brain. On the other hand, although a wealth of data exists about the neural circuitry that is concerned with the perception of self-motion variables such as the current direction of travel, little research has been devoted to investigating how this neural circuitry may relate to active steering control. Here we present a cortical neural network model for visually guided navigation that has been embodied on a physical robot exploring a real-world environment. The model includes a rate based motion energy model for area V1, and a spiking neural network model for cortical area MT. The model generates a cortical representation of optic flow, determines the position of objects based on motion discontinuities, and combines these signals with the representation of a goal location to produce motor commands that successfully steer the robot around obstacles toward the goal. The model produces robot trajectories that closely match human behavioral data. This study demonstrates how neural signals in a model of cortical area MT might provide sufficient motion information to steer a physical robot on human-like paths around obstacles in a real-world environment, and exemplifies the importance of embodiment, as behavior is deeply coupled not only with the underlying model of brain function, but also with the anatomical constraints of the physical body it controls.

In applications employing Multiple Unmanned Marine Vehicles (MUMVs), the navigation has a very great importance to guarantee formation preservation and collision avoidance. While single vehicles usually base their navigation on absolute measurements (GPS, inertial navigation) to determine their position relative to the world, it may be reasonable to perform a relative navigation within vehicle teams. In this paper, we propose relative team navigation based on Kalman Filters to enable a velocity controller to establish a close formation under the typical marine constraints (narrow band width communication with low reliability). We will simulate a team of three marine vehicles and compare the results of different strategies for team navigation. Fig. 1. Marine Habitat Mapping

The implementation of a set of visually based behaviors for navigation is presented. The approach, which has been inspired by insect's behaviors, is aimed at building a "library" of embedded visually guided behaviors coping with the most common situations encountered during navigation in an indoor environment. Following this approach, the main goal is no longer how to characterize the envikronment, but how to embed in each behavior the perceptual processes necessary to understand the aspects of the environment required to generate a purposeful motor output.

Navigation and obstacle avoidance belong to the basic behavioral repertoire of any biological or technical autonomous agent. A moving observer equipped with a monocular visual sensor can gain information pertinent for the performance of these tasks from the optical ow eld induced by its own motion. In the periphery of the visual eld image ow can be evaluated for speed and direction control, whereas the central ow indicates imminent collisions. We show that a spacevariant mapping augmented with a purposive representation of the environment allows a robot to take into account these structural properties of the ow eld and to navigate in real-time in an unknown environment. We implemented an extended simulation environment, and veri ed reliability, speed, control and robustness of our proposed scheme.

Navigation and obstacle avoidance belong to the basic behavioral repertoire of any biological or technical autonomous agent. A moving observer equipped with a monocular visual sensor can gain information pertinent for the performance of these tasks from the optical ow eld induced by its own motion. In the periphery of the visual eld image ow can be evaluated for speed and direction control, whereas the central ow indicates imminent collisions. We show that a spacevariant mapping augmented with a purposive representation of the environment allows a robot to take into account these structural properties of the ow eld and to navigate in real-time in an unknown environment. We implemented an extended simulation environment, and veri ed reliability, speed, control and robustness of our proposed scheme.

In this paper, we introduce a high-level software simulator for teams of unmanned marine surface and underwater crafts. The work was performed in the framework of the European Research project GREX. This project has the goal to realise cooperation between heterogeneous marine vehicles by creating a conceptual framework and middleware system. The natural constraints of marine missions must be kept in mind. In underwater scenarios there is no global positioning available like GPS. The research in underwater communication is at present time at its very beginning. For the validation of different control strategies, there is the need for a high-level software simulator that is able to evaluate different approaches and to judge them according to their requirements in navigation and communication. Therefore, the above-mentioned constraints of reality must be realised within the simulator. All interfaces in the simulator need to be the same as in reality. So it is possible to use and to tes...

In applications employing multiple unmanned marine vehicles (MUMVs), the navigation has a very great importance to guarantee formation preservation and collision avoidance. While single vehicles usually base their navigation on absolute measurements (GPS, inertial navigation) to determine their position relative to the world, it may be reasonable to perform a relative navigation within vehicle teams. In this paper, we propose relative team navigation based on Kalman Filters to enable a velocity controller to establish a close formation under the typical marine constraints (narrow band width communication with low reliability). We will simulate a team of three marine vehicles and compare the results of different strategies for team navigation.

In this paper, we present a new method for vision-based, reactive robot navigation that enables a robot to move in the middle of the free space by exploiting both central and peripheral vision. The system employs a forward-looking camera for central vision and two side-looking cameras for sensing the periphery of the robot's visual field. The developed method combines the information acquired by this trinocular vision system and produces low-level motor commands that keep the robot in the middle of the free space. The approach follows the purposive vision paradigm in the sense that vision is not studied in isolation but in the context of the behaviors that the system is engaged as well as the environment and the motor capabilities of the robot. It is demonstrated that by taking into account these issues, vision processing can be drastically simplified, still giving rise to quite rich behaviors. The advantages of the method is that it does not make strict assumptions about the environment, it requires very low level information to be extracted from the images, it produces a robust robot behavior and it is computationally very efficient. Results obtained by both simulations and from a prototype on-line implementation demonstrate the effectiveness of the method.