Autonomous Driving of Mobile Robots in Dynamic Environments Based on Deep Deterministic Policy Gradient: Reward Shaping and Hindsight Experience Replay.

In this paper, we propose a reinforcement learning-based end-to-end learning method for the autonomous driving of a mobile robot in a dynamic environment with obstacles. Applying two additional techniques for reinforcement learning simultaneously helps the mobile robot in finding an optimal policy to reach the destination without collisions. First, the multifunctional reward-shaping technique guides the agent toward the goal by utilizing information about the destination and obstacles.

The Task Decomposition and Dedicated Reward-System-Based Reinforcement Learning Algorithm for Pick-and-Place.

This paper proposes a task decomposition and dedicated reward-system-based reinforcement learning algorithm for the Pick-and-Place task, which is one of the high-level tasks of robot manipulators. The proposed method decomposes the Pick-and-Place task into three subtasks: two reaching tasks and one grasping task. One of the two reaching tasks is approaching the object, and the other is reaching the place position.

Different unilateral force control strategies between athletes and non-athletes.

This study investigated continuous visuomotor tracking capabilities between athletes and non-athlete controls using isometric force control paradigm. Nine female athletes and nine female age-matched controls performed unilateral hand-grip force control tasks with their dominant and non-dominant hands at 10% and 40% of maximal voluntary contraction (MVC), respectively. Three conventional outcome measures on force control capabilities included mean force, force accuracy, and force variability, and we additionally calculated two nonlinear dynamics variables including force regularity using sample entropy and force stability using maximal Lyapunov exponent.

Preparation of easily chewable and swallowable texture-modified .

This study aimed to develop texture-modified (TMD) that is safe, well-shaped, and easy to chew and swallow. As the fermentation proceeded, the pH decreased, and the total acidity and total number of lactic acid bacteria increased. The hardness of the TMD decreased significantly by more than 96% (< 0.

Application of freeze-thaw enzyme impregnation to produce softened root vegetable foods for elderly consumers.

The aims of this study were to determine the viability of using freeze-thaw infusion (FI) technology to produce a range of root vegetables using enzyme treatments with improved texture characteristics for elderly consumers with swallowing difficulties. We applied enzyme impregnation as a technology to soften the textures of root vegetables commonly consumed in Korea; balloon flower root (Platycodon grandiflorus), burdock root (Arctium lappa L.), carrot (Daucus carota L.