Multi-Resolution, Multi-Heuristic, Bezier Curve Based, A* Motion Planning With Semantic Consideration

CSEF · 2023 Mathematical Sciences Third Award

Overview

Robotic control is often divided into four categories: mapping, localization, path planning, and control. Recent innovations related to path planning often center around search-based planning, which searches a given environment for an optimal route, where optimality could be defined by time, distance, or smoothness. However, most sampling planners are based on a grid format and fail to take into account the kinematics of the robot. Prior works have investigated the use of curve-based search planners. However, these planners suffer from high computation expenses. Thus, we propose a Bezier curve-based motion planner with multi-resolution, multi-heuristic, and semantic-based planning, allowing for the benefits of curved planning to be realized without the expense of traditional curve planning. By sampling constant acceleration control at multiple resolutions, the state space, all possible velocities, and positions of the robot can be sampled faster, allowing for the rapid generation of a curved trajectory, incorporating the kinematics of a mobile robot. Moreover, the use of Bezier representations allows for faster obstacle detection via triangle rasterization. In randomly generated environments and environments with large obstacles, the Bezier algorithm generated optimal solution results more rapidly than the traditional method, as proven by multiple matched-pair t-tests with P-Values of essentially zero. Robots are becoming more prevalent in daily activities ranging from autonomous cars to drone delivery systems. The proposed Bezier curve planning would potentially alleviate the societal burden by saving millions of lives and dollars on the roads while making daily life more accessible and efficient through the improved efficiency and safety of robot systems.

Source coverage

This record comes from a published award list, not a complete project archive. Its abstract comes from CSEF's public project showcase as archived by the Internet Archive before judging (https://web.archive.org/web/20230401224130/https://ca-csef.zfairs.com/showcase/ShowcaseInfo?f=838e60b7-ea75-46e8-865c-fde4864244b3); the version presented may differ.

Awards (1)

Competition history

  • CSEF 2023 Mathematical Sciences · Entry S1403

Resources

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Source: California Science & Engineering Fair public projects

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google