MIT Researchers Develop Collision-Free Motion Planning for Robots Using Sum-of-Squares Programming

Wednesday - March 13 2024, 23:45 UTC - 8 months ago

MIT researchers have developed a new safety check technique for robots, ensuring 100% accuracy in collision-free motion planning. The technique, which uses sum-of-squares programming, is capable of quickly solving complex motion problems and has potential applications in various industries. It provides a mathematical proof of collision avoidance, adding an extra layer of assurance for users.

As robots become more integrated into our lives, ensuring their safety is of utmost importance. However, traditional safety check algorithms used by robots to plan their motion often result in false positives, making them unsuitable for real-world use. In light of this, researchers at MIT have developed a new safety check technique that guarantees 100% accuracy in collision-free trajectory planning.

This new technique, which makes use of sum-of-squares programming, is able to accurately account for even the smallest differences in trajectory, taking only a few seconds to generate proof. As lead author Alexandre Amice explains, "With this work, we have shown that you can solve some challenging problems with conceptually simple tools. Sum-of-squares programming is a powerful algorithmic idea, and while it doesn't solve every problem, if you are careful in how you apply it, you can solve some pretty nontrivial problems." .

The potential applications of this research are vast, particularly in scenarios where robots must work quickly and safely in crowded environments. This includes food preparation robots in commercial kitchens, as well as robot assistants in home health care settings. What sets this technique apart from others is its ability to continuously monitor the robot's trajectory, rather than performing static checks at specified intervals. This allows for greater accuracy and efficiency in collision avoidance.

The algorithm used in this research works by creating a mathematical model of the robot and its environment. It then calculates the clearance the robot has at various points in its trajectory, creating a conservative safety boundary that surrounds the area the robot may move through. This proves to be a more efficient and accurate method of ensuring collision-free motion, compared to traditional simulation-based safety checks.

This technique not only provides accurate collision avoidance, but it also generates a mathematical proof that can be quickly checked using simple math. This adds an extra layer of assurance for users, allowing them to trust in the robot's ability to safely navigate its environment. With its ability to solve complex motion planning problems, this method has the potential to greatly improve the safety and efficiency of robots in various industries.

The researchers' work will be presented at the International Conference on Robots and Automation in May 2024. The full paper is currently available on the arXiv preprint server.