Jorge Bruno Silva

Timed trajectory generation for a toy-like wheeled robot

In this work, we address temporal stabilization of generated movements in autonomous robotics. We focus on generating movement for a mobile robot, that must reach a target location within a constant time. Target location is online calculated by using the robot visual system, such that action is steered by the sensory information. This is a very critical issue in several robotic tasks including: catching, hitting, and humanrobot scenarios. Robot velocity is controlled through an Hopf oscillator, adapted according to temporal feedback. Timing of the velocity profile is modulated according to an adaptive mechanism that enables setting different times for acceleration and deceleration. Results on a DRK8000 mobile robot confirm the system¿s reliability with low-level sensors.

Dynamical system approach for obstacle avoidance in a Smart Walker device

The need for Smart Walkers to help navigation of elderly is increasing rapidly. This paper proposes an approach based on the Dynamical System Approach for obstacle avoidance of a Smart Walker device. Layers of sonars are distributed on the walker for detecting obstacles and stairs. A simulated model of the ASBGo Walker [1] and several realistic simulations in a hospital environment with typical hospital obstacles illustrate the good performance of the approach.

Dynamical systems in robot control architectures: A building block perspective

The paper reviews a known robot control architecture using nonlinear analysis and control theory viewpoints. The architecture is based on a mesh of dynamic systems and feedthrough maps and is able to drive the robot under temporal constraints. The analysis points to an intuitive, though innovative, conclusion that control architectures can be constructed from a methodological perspective by mixing (i) dynamical systems with fixed points carefully selected to match mission requirements, and (ii) feedthrough maps that perform memoryless transformations on input data. Experiments using the Webots environment are presented to illustrate the ideas developed.

A Stability Analysis for a Dynamical Robot Control Architecture

Abstract This paper addresses the feedback stabilization for a navigation architecture applied to wheeled mobile robots based on a mesh of nonlinear dynamical systems and feedthrough maps. The architecture provides a suitable robots direction to avoid obstacles, while generating an appropriated velocity for the robot to complete its mission under temporal constraints. Mission success is analyzed as a stability problem using concepts from nonlinear analysis and control. Simulations of missions consisting on a mobile robot moving in an indoor environment illustrate the ideas developed.

Timed Trajectory Generation Combined with an Extended Kalman Filter for a Vision-Based Autonomous Mobile Robot

Planning collision-free trajectories requires the combination of generation and modulation techniques. This is especially important if temporal stabilization of the generated trajectories is considered. Temporal stabilization means to conform to the planned movement time, in spite of environmental conditions or perturbations. This timing problem has not been addressed in most current robotic systems, and it is critical in several robotic tasks such as sequentially structured actions or human-robot interaction. This work focuses on generating trajectories for a mobile robot, whose goal is to reach a target within a constant time, independently of the world complexity. Trajectories are generated by nonlinear dynamical systems. Herein, we extend our previous work by including an Extended Kalman Filter (EKF) to estimate the target location relative to the robot. A simulated hospital environment and a Pioneer 3-AT robot are used to demonstrate the robustness and reliability of the proposed approach in cluttered, dynamic and uncontrolled scenarios. Multiple experiments confirm that the inclusion of the EKF preserves the timing properties of the overall architecture.

Generating trajectories with temporal constraints for an autonomous robot

Trajectory modulation and generation are two fundamental issues in the path planning problem in autonomous robotics, specially considering temporal stabilization of the generated movements. This is a very critical issue in several robotic tasks including: catching, hitting, and human-robot scenarios.

A robot control architecture supported on contraction theory

ABSTRACT This paper proposes fundamentals for stability and success of a global system composed by a mobile robot, a real environment and a navigation architecture with time constraints. Contraction theory is a typical framework that provides tools and properties to prove the stability and convergence of the global system to a unique fixed point that identifies the mission success. A stability indicator based on the combination contraction property is developed to identify the mission success as a stability measure. The architecture is fully designed through C1 nonlinear dynamical systems and feedthrough maps, which makes it amenable for contraction analysis. Experiments in a realistic and uncontrolled environment are realised to verify if inherent perturbations of the sensory information and of the environment affect the stability and success of the global system.

A Modified LGMD Based Neural Network for Automatic Collision Detection

Robotic collision detection is a complex task that requires both real time data acquisition and important features extraction from a captured image. In order to accomplish this task, the algorithms used need to be fast to process the captured data and perform real time decisions. Real-time collision detection in dynamic scenarios is a hard task if the algorithms used are based on conventional techniques of computer vision, since these arecomputationally complex and, consequently, time-consuming, specially if we consider small robotic devices with limited computational resources. On the other hand, neurorobotic models may provide a foundation for the development of more effective and autonomous robots, based on an improved understanding at the biological basis of adaptive behavior. Particularly, our approach must be inspired in simple neural systems, which only requires a small amount of neural hardware to perfom complex behaviours and, consequently, becomes easier to understand all the mechanism behind these behaviours. By this reason, flying insects are particularly attractive as sources of inspiration due to the complexity and efficiency of the behaviours allied with the simplicity of a reduced neural system. The Lobula Giant Movement Detector (LGMD) is a wide-field visual neuron located in the Locust optic lobe. It responds selectively to looming objects and can trigger avoidance reactions when a rapidly approaching object is detected. Based on the relatively simple encoding strategy of the LGMD neuron, different bio-inspired neural networks for collision avoidance were developed. In the work presented in this chapter, we propose a new LGMD model based on two previous models, in order to improve over them by incorporating other features. To accomplish this goal, we proceed as follows: (1) we critically analyse different LGMD models proposed in literature; (2) we highlight the convergence or divergence in the results obtained with each of the models; (3) we merge the advantages/disadvantages of each model into a new one. In order to assess the real-time properties of the proposed model, it was applied to a real robot. The obtained results have shown the high capability and robustness of the LGMD model to prevent collisions in complex visual scenarios.

Developing a timed navigation architecture for hospital delivery robots

In hospitals, typical tasks of delivering goods between different locations are usually done by auxiliary staff. With the development of robotic technologies, such tasks can be performed by mobile robots releasing the staff effort to other tasks. In order to successfully complete the tasks of delivering goods inside hospitals, mobile robots should be able to generate trajectories free of collisions. In addition, including timing constraints to the generated trajectories has not been addressed in most current robotic systems, and it is critical in robotic tasks as human-robot interaction. Including timing constraints means to obey to the planned movement time, despite diversified environmental conditions or perturbations. In this paper we aim to develop a navigation architecture with timing constraints based on a mesh of nonlinear dynamical systems and feedthrough maps for wheeled mobile robots. A simulated hospital environment and a wheeled robot pioneer 3-DX are used to demonstrate the robustness and reliability of the proposed architecture in cluttered, dynamic and uncontrolled hospital scenarios.

Field results of a navigation architecture with timing constraints

This paper presents results of field tests of a mobile robot controlled by a navigation architecture accounting for timing constraints in an indoor environment. Dependability properties characterize the effects of disturbances on the ability to successfully accomplish any assigned missions, described in terms of the stability of an equilibrium state identified with a goal location. The stability is analyzed using Contraction theory. A localization system based on artificial landmarks is used to obtain location estimates that enable the robot to autonomously cover large distances. Monte Carlo tests assess the architecture under different real environment conditions including recovering from disturbing events such as landmark detection failures, robot kidnapping, unexpected collisions, and changes in the density of obstacles in the environment. Tests include long-run missions of around 2900 m lasting for 4.5 hours.