Open-Source, Cost-Aware Kinematically Feasible Planning for Mobile and Surface Robotics

Open-Source, Cost-Aware Kinematically Feasible Planning for Mobile and Surface Robotics

23 Jan 2024 | Steve Macenski, Matthew Booker, Joshua Wallace
This paper introduces the Smac Planner, an open-source, search-based planning framework designed for mobile and surface robotics. The framework includes multiple algorithm implementations such as 2D-A*, Hybrid-A*, and State Lattice planners. The main contributions of the paper are threefold: 1. **Framework Description**: It provides a minimal open-source software framework that allows easy integration of search-based planners. 2. **Cost-Aware Planners**: It introduces new variations of feasible planners tailored to the needs of mobile robotics, including Cost-Aware 2D-A*, Cost-Aware Hybrid-A*, and Cost-Aware State Lattice planners. 3. **Benchmarking**: It provides performance benchmarking against other standard planning frameworks, demonstrating the effectiveness and efficiency of the Smac Planners. The Smac Planner is significant because it has become the standard open-source planning system within ROS 2's Nav2 framework, powering thousands of robots in research and industry. The paper also discusses related work, the design of the Smac Planner framework, and the implementation details of the Cost-Aware planners. Experiments in both synthetic and real-world environments show that the Smac Planners outperform existing planners in terms of runtime and path quality, making them suitable for a wide range of mobile robotics applications.This paper introduces the Smac Planner, an open-source, search-based planning framework designed for mobile and surface robotics. The framework includes multiple algorithm implementations such as 2D-A*, Hybrid-A*, and State Lattice planners. The main contributions of the paper are threefold: 1. **Framework Description**: It provides a minimal open-source software framework that allows easy integration of search-based planners. 2. **Cost-Aware Planners**: It introduces new variations of feasible planners tailored to the needs of mobile robotics, including Cost-Aware 2D-A*, Cost-Aware Hybrid-A*, and Cost-Aware State Lattice planners. 3. **Benchmarking**: It provides performance benchmarking against other standard planning frameworks, demonstrating the effectiveness and efficiency of the Smac Planners. The Smac Planner is significant because it has become the standard open-source planning system within ROS 2's Nav2 framework, powering thousands of robots in research and industry. The paper also discusses related work, the design of the Smac Planner framework, and the implementation details of the Cost-Aware planners. Experiments in both synthetic and real-world environments show that the Smac Planners outperform existing planners in terms of runtime and path quality, making them suitable for a wide range of mobile robotics applications.
Reach us at info@study.space