New Algorithm Helps Mobile Robots Navigate Obstacles

Researchers at the University of South Australia have written a computational algorithm that allows mobile robots to navigate obstacles, finding the quickest path to their destination.

New Algorithm Helps Mobile Robots Navigate Obstacles.
Image Credit: University of South Australia. (2022). Algorithm helps robots avoid obstacles in their path. [online] Available at: https://www.unisa.edu.au/media-centre/Releases/2022/algorithm-helps-robots-avoid-obstacles-in-their-path/

In the Journal of Field Robotics, the Australian researchers describe how they programmed the best elements from existing algorithms into a TurtleBot to enable it to adjust its speed and steering angles.

There are two types of path planning strategies for mobile robots, depending on whether they are being used in fixed environments or where they are encountering moving obstacles, such as humans or machines.

Dr. Habib Habibullah, Engineering Lecturer, University of South Australia

A Brief Introduction to Mobile Robots

Mobile robots are machines controlled by artificial intelligence software (algorithms) that use tracks, wheels or “legs” to navigate their environment.

Mobile robots can operate in many types of environments. These include aerial robots such as drones, polar robots, unmanned ground vehicles, autonomous underwater vehicles and delivery robots. Mobile robots can either operate autonomously or under guidance.

Guided robots are guided by tracks or other sorts of guidance systems. They often require the supervision of an operator. Autonomous mobile robots (AMRs), on the other hand, navigate independently from external guidance.

To achieve this, AMRs are controlled by artificial intelligence software incorporating machine learning and specialized path planning algorithms. Additionally, cameras and sensors help them locate and avoid obstacles.

In 1979, the Stanford Cart was the first mobile robot to successfully navigate a room without human intervention. A computer algorithm was written to process images captured from an onboard camera, thus enabling the cart to navigate.

Ever since then, industries such as agriculture, logistics and healthcare have sought to use autonomous mobile robots to improve their processes. Navigation is only truly autonomous once a robot can navigate to its destination in a reasonable amount of time, without human intervention.

Therefore, these robots must be able to negotiate obstacles successfully. The difficulty, however, is compounded because obstacles may not always be stationary.

Path Planning Algorithms for Mobile Robots

Path planning is essential to enable autonomous mobile robots to negotiate obstacles successfully. Their optimal path must be collision-free from starting point to destination, taking into account distance traveled, time taken and cost of operation. Path planning can be conducted either in an unknown environment or a known environment where obstacles have already been mapped.

Researchers have written many algorithms that tackle path planning problems for mobile robots. These include so-called genetic algorithms which model evolutionary behavior, fuzzy logic algorithms and neural network algorithms. Others carry exotic names such as ant colony optimization, particle swarm optimization, artificial bee colony and shuffled frog leaping algorithm.

Some path planning strategies employ reactive navigation, where the path planning process occurs while the robot is moving (online). These strategies rely upon real-time feedback from onboard sensors.

The Artificial Potential Field (APF) method is such a method. It guides the robot to its destination using artificially induced attractive and repulsive forces. Vector field histogram (VFH) is another such method. It updates a two-dimensional cartesian histogram grid as the robot is moving.

Recognizing the strengths and weaknesses of existing methods, the Australian team incorporated the best from each into their own custom-written algorithm. They tested their method against two readily available algorithms: Artificial Potential Field (APF) just mentioned and Dynamic Window Approach (DWA). DWA, like APF, is an online path planning (collision avoidance) algorithm.

Dr. Habibullah and his team tested nine different scenarios in which they compared times to destination, collision rates and average speeds of the robot.

The Australian-built algorithm successfully navigated each scenario without any collisions. In contrast, the DWA algorithm resulted in 3 collisions, a 66% success rate. The APF model was collision-free, but the robot took longer to reach its destination.

Our proposed method sometimes took a longer path, but it was faster and safer, avoiding all collisions.

Dr. Habib Habibullah, Engineering Lecturer, University of South Australia

The Australian researchers believe their algorithm will be useful in many industrial scenarios, including warehouses, restaurants and farms where robots could be used for picking, packing and pelletizing.

References and Further Reading

Hossain, T. et al. (2021) Local path planning for autonomous mobile robots by integrating modified dynamic‐window approach and improved follow the gap method. Journal of field robotics, [online]. Available at: https://onlinelibrary.wiley.com/doi/full/10.1002/rob.22055

Patle, B. K. et al. (2019). A review: On path planning strategies for navigation of mobile robot. Defence technology, [online] 15(4), pp. 582–606. Available at: https://www.researchgate.net/publication/332717157_A_review_On_path_planning_strategies_for_navigation_of_mobile_robot

University of South Australia. (2022). Algorithm helps robots avoid obstacles in their path. [online] Available at: https://www.unisa.edu.au/media-centre/Releases/2022/algorithm-helps-robots-avoid-obstacles-in-their-path/

Stanley Innovation. 12 of the most innovative and groundbreaking mobile robots. [online] Available at: https://stanleyinnovation.com/12-coolest-mobile-robots/

Disclaimer: The views expressed here are those of the author expressed in their private capacity and do not necessarily represent the views of AZoM.com Limited T/A AZoNetwork the owner and operator of this website. This disclaimer forms part of the Terms and conditions of use of this website.

William Alldred

Written by

William Alldred

William Alldred is a freelance B2B writer with a bachelor’s degree in Physics from Imperial College, London. William is a firm believer in the power of science and technology to transform society. He’s committed to distilling complex ideas into compelling narratives. Williams’s interests include Particle & Quantum Physics, Quantum Computing, Blockchain Computing, Digital Transformation and Fintech.

Citations

Please use one of the following formats to cite this article in your essay, paper or report:

  • APA

    Alldred, William. (2022, January 11). New Algorithm Helps Mobile Robots Navigate Obstacles. AZoRobotics. Retrieved on October 16, 2024 from https://www.azorobotics.com/News.aspx?newsID=12682.

  • MLA

    Alldred, William. "New Algorithm Helps Mobile Robots Navigate Obstacles". AZoRobotics. 16 October 2024. <https://www.azorobotics.com/News.aspx?newsID=12682>.

  • Chicago

    Alldred, William. "New Algorithm Helps Mobile Robots Navigate Obstacles". AZoRobotics. https://www.azorobotics.com/News.aspx?newsID=12682. (accessed October 16, 2024).

  • Harvard

    Alldred, William. 2022. New Algorithm Helps Mobile Robots Navigate Obstacles. AZoRobotics, viewed 16 October 2024, https://www.azorobotics.com/News.aspx?newsID=12682.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.