This paper provides a new deterministic Q-learning with a presumed knowledge about the distance from the current state to both the next state and the goal. This knowledge is efficiently used to update the entries in the Q-table once only by utilizing four derived properties of the Q-learning, instead of repeatedly updating them like the classical Q-learning. Naturally, the proposed algorithm has an insignificantly small time complexity in comparison to its classical counterpart. Furthermore, the proposed algorithm stores the Q-value for the best possible action at a state and thus saves significant storage. Experiments undertaken on simulated maze and real platforms confirm that the Q-table obtained by the proposed Q-learning when used for the path-planning application of mobile robots outperforms both the classical and the extended Q-learning with respect to three metrics: traversal time, number of states traversed, and 90° turns required. The reduction in 90° turnings minimizes the energy consumption and thus has importance in the robotics literature.

Memetic algorithms (MAs) are population-based meta-heuristic search algorithms that combine the composite benefits of natural and cultural evolutions. An adaptive MA (AMA) incorporates an adaptive selection of memes (units of cultural transmission) from a meme pool to improve the cultural characteristics of the individual member of a population-based search algorithm. This paper presents a novel approach to design an AMA by utilizing the composite benefits of differential evolution (DE) for global search and Q-learning for local refinement. Four variants of DE, including the currently best self-adaptive DE algorithm, have been used here to study the relative performance of the proposed AMA with respect to runtime, cost function evaluation, and accuracy (offset in cost function from the theoretical optimum after termination of the algorithm). Computer simulations performed on a well-known set of 25 benchmark functions reveal that incorporation of Q-learning in one popular and one outstanding variants of DE makes the corresponding algorithm more efficient in both runtime and accuracy. The performance of the proposed AMA has been studied on a real-time multirobot path-planning problem. Experimental results obtained for both simulation and real frameworks indicate that the proposed algorithm-based path-planning scheme outperforms the real-coded genetic algorithm, particle swarm optimization, and DE, particularly its currently best version with respect two standard metrics defined in the literature.

In this paper, we discuss the development of cost effective, wireless and wearable vibrotactile haptic device for stiffness perception during an interaction with virtual objects. Our experimental setup consists of haptic device with five vibrotactile actuators, virtual reality environment tailored in Unity 3D integrating the Oculus Rift Head Mounted Display(HMD) and the Leap Motion controller.The virtual environment is able to capture touch inputs from users. Interaction forces are then rendered at 500Hz and fed back to the wearable setup stimulating fingertips with ERM vibrotactile actuators. Amplitude and frequency of vibrations are modulated proportionally to the interaction force to simulate the stiffness of a virtual object. A quantitative and qualitative study is done to compare the discrimination of stiffness on virtual linear spring in three sensory modalities: visual only feedback, tactile only feedback and their combination. A common psychophysics method called the Two Alternative Forced Choice (2AFC) approach is used for quantitative analysis using Just Noticeable Difference(JND) and Weber Fractions(WF). According to the psychometric experiment result, average Weber fraction values of 0.39 for visual only feedback was improved to 0.25 by adding the tactile feedback.