We present a modular controller for quadruped locomotion over unperceived rough terrain. Our approach is based on a computational Central Pattern Generator (CPG) model implemented as coupled nonlinear oscillators. Stumbling correction reflex is implemented as a sensory feedback mechanism affecting the CPG. We augment the outputs of the CPG with virtual model control torques responsible for posture control. The control strategy is validated on a 3D forward dynamics simulated quadruped robot platform of about the size and weight of a cat. To demonstrate the capabilities of the proposed approach, we perform locomotion over unperceived uneven terrain and slopes, as well as situations facing external pushes.

We present a general approach to design modular controllers for limit cycle locomotion over unperceived rough terrain. The control strategy uses a Central Pattern Generator (CPG) model implemented as coupled nonlinear oscillators as basis. Stumbling correction and leg extension reflexes are implemented as feedbacks for fast corrections, and model-based posture control mechanisms define feedbacks for continuous corrections. The control strategy is validated on a detailed physics-based simulated model of a compliant quadruped robot, the Oncilla robot. We demonstrate dynamic locomotion with a speed of more than 1.5 BodyLength/s over unperceived uneven terrains, steps, and slopes.

Most of the central pattern generator (CPG) models are based on defining explicit dynamical systems and finding the appropriate parameters. In this paper, we propose a novel CPG model that is based on altering a nonlinear oscillator to obtain desired limit cycle behavior. This CPG model benefits from an explicit basin of attraction and also fast convergence behavior. The presented CPG model is used in an imitation model that tries to learn the proper periodical behavior by looking at a mentor. First, a mentor performs the desired periodical behavior. Then, a hand-eye coordination process, inspired from infant babbling, is initiated to extract proper motor actions from what is observed. The extracted motor actions are finally embedded into the CPG model for smooth reproduction. This imitation model is implemented on a robotic marionette behavior learning task. The outcome of the final performance of the robotic marionette is behaviorally understandable smooth actions.

In this paper, we propose a fast algorithm for gesture recognition based on the saliency maps of visual attention. A tuned saliency-based model of visual attention is used to find potential hand regions in video frames. To obtain the overall movement of the hand, saliency maps of the differences of consecutive video frames are overlaid. An improved characteristic loci feature extraction method is introduced and used to code obtained hand movement. Finally, the extracted feature vector is used for training SVMs to classify the gestures. The proposed method along a hand-eye coordination model is used to play a robotic marionette and an approval/rejection phase is used to interactively correct the robotic marionette's behavior.

Currently, genetic algorithms (GA) are widely used in different optimization problems. One of the problems with GAs is tuning their parameters correctly as they can have a significant effect on GA's overall performance. Till now, different methods have been proposed for fine tuning these parameters. Many of these methods use fuzzy linguistic rules in order to find the correct parameters in each stage of the GA evolution. But these methods look at each chromosome as a whole solution for a specific problem. In our contribution, a new method has been proposed which breaks each chromosome into sub-parts and uses the better sub-solutions as the building blocks of the next generation using a fuzzy-based approach. The performance of this algorithm has been shown on the traveling salesman problem (TSP) with comparison to simple GA and adaptive GA.