An Efficient Navigation Framework for Autonomous Mobile Robots in Dynamic Environments using Learning Algorithms

In this paper, we propose an efficient navigation framework for autonomous mobile robots in dynamic environments using a combination of a reinforcement learning algorithm and a neural network model. The main idea of the proposed algorithm is to provide the mobile robots the relative position and motion of the surrounding objects to the robots, and the safety constraints such as minimum distance from the robots to the obstacles, and a learning model. We then distribute the mobile robots into a dynamic environment. The robots will automatically learn to adapt to the environment by their own experienced through the trial-and-error interaction with the surrounding environment. When the learning phase is completed, the mobile robots equipped with our proposed framework are able to navigate autonomously and safely in the dynamic environment. The simulation results in a simulated environment shows that, our proposed navigation framework is capable of driving the mobile robots to avoid dynamic obstacles and catch up dynamic targets, providing the safety for the surrounding objects and the mobile robots.

Quadratic Sensitivity Analysis of Fixtures and Locating Schemes for Rigid Parts

The main purpose of locating schemes are to position parts. The locating scheme utilizes tooling elements, referred to as locators, to introduce geometric constraints. A rigid part is uniquely positioned when it is brought into contact with the locators. By using kinematic analysis we derive a quadratic sensitivity equation that relates position error in locators with the resulting displacement of the part held by the locating scheme. The sensitivity equation which depends on the locator positions and the workpiece geometry around the contact points can be used for locating scheme evaluation, robust fixture design, tolerancing and diagnosis. The quadratic sensitivity equation derived in this paper is novel by adequate dealing with locator contact at nonprismatic surfaces, nonsmall errors, locator error interaction effects and locator errors in arbitrary directions. Theory for comparing the relative gain in precision by using the quadratic sensitivity equation instead of the linear is developed. The practical relevance of the quadratic sensitivity equation is tested through numerical experiments.