Perception triggered response behavior together with the selection of the appropriate environmental cues can properly guide the robot towards its goal. But often landmarks are difficult to be recognised by the robot; these difficulties are increased due to the morphology of the robot and its movements. Dynamic orientation of the camera’s parameters, fixing the attention of the visual system on ...

gait rehabilitation using body weight support on a treadmill is a recommended rehabilitation technique for neurological injuries, such as spinal cord injury. in this paper, a new robotic orthosis is presented for treadmill training. in the presented design the criteria such as low inertia of robot components, backdrivability, high safety and degrees of freedom based on human walking are conside...

In recent years there is a growing interest in multi-robots systems, where a group of N robots are working collaboratively in order to execute a given task. This thesis addresses two open challenges in multi-robot systems. The first is the challenge of deciding on which robot, out of a group of robots, should travel to a goal location, to carry out a task there. The second is the challenge of i...

In this paper, we discuss the design and engineering of the PolyBot board, a custom robot controller board. This board has many features which make it suitable for use in the design and construction of a simple mobile robot. We outline the design decisions made such as: microcontroller selection, input and output features, board layout, connector selection, and software. We discuss our experien...

This work presents the development and implementation of a biologically inspired navigation system on the autonomous Psikharpax rodent robot. Our system comprises two independent navigation strategies: a taxon expert and a planning expert. The presented navigation system allows the robot to learn the optimal strategy in each situation, by relying upon a strategy selection mechanism. Keywords— R...

in this article a new and an accurate method for kinematic and dynamic analysis of a parallel robot 3prs and a hybrid robot (parallel and serial) 3prs-rrp are presented, which is based on the denavit-hartenberg transformation matrix algebra. first, basic properties of various kinds of robots are compared, and then the denavit-hartenberg parameters and their table are introduced. next, the metho...

A learning system composed of linear control modules, reinforcement learning modules and selection modules (a hybrid reinforcement learning system) is proposed for the fast learning of real-world control problems. The selection modules choose one appropriate control module dependent on the state. This hybrid learning system was applied to the control of a stilt-type biped robot. It learned the ...

We propose Markov random fields (MRFs) as a probabilistic mathematical model for unifying approaches to coordination among multi-robot and cyber-physical systems or, more specifically, distributed action selection. The MRF model is well-suited to domains in which the joint probability over latent (action) and observed (perceived) variables can be factored into pairwise interactions between thes...

The robot studies generally deal with only communication between one robot and one person there have been few discussions of the communication between a robot and plural persons This paper proposes a method enables robot to communicate with plural persons using the selection priority of the partner based on the concept of Proxemics In this method a robot changes sensory motor modality based on ...

Navigation based on detected landmarks is an important facet of robot navigation. This work investigates into a qualitative representation of landmarks for an autonomous learning task where a robot learns a goal directed navigation strategy with reinforcement learning. We discuss how to build a suitable landmark-based representation. In particular, we focus on selection of landmarks to regard w...