{"id":294,"date":"2025-12-22T16:35:56","date_gmt":"2025-12-22T16:35:56","guid":{"rendered":"https:\/\/intention.put.poznan.pl\/?p=294"},"modified":"2025-12-22T16:53:02","modified_gmt":"2025-12-22T16:53:02","slug":"robust-localization-mapping-and-navigation-for-quadruped-robots","status":"publish","type":"post","link":"https:\/\/intention.put.poznan.pl\/?p=294","title":{"rendered":"Robust Localization, Mapping, and Navigation for Quadruped Robots"},"content":{"rendered":"\n

Navigation is challenging for quadruped robots. This is even more problematic when using small robots, where we have to mount cheap sensors due to payload and cost reasons.<\/p>\n\n\n\n

The problem gets even more challenging if we are using policies learned with Reinforcement Learning<\/strong>: these policies are robust, but may cause jerky movements, causing localization loss.<\/p>\n\n\n\n

As perception is a fundamental component of INTENTION, we decided to tackle this problem, in collaboration with Prof. Matteo Luperto<\/a> at Universit\u00e0 Degli Studi di Milano and with our visiting scholar, Dyuman Aditya<\/a>.<\/p>\n\n\n

\"\"<\/figure>\n\n\n

Our system leverages data from low-cost sensors<\/strong>\u2014including an RGB-D camera, an IMU, and joint encoders\u2014augmented by scan stabilization <\/strong>and leg odometry <\/strong>modules to achieve accurate localization and mapping. These modules are essential for quadruped robots equipped with reactive, high-speed controllers to effectively navigate complex 2D environments.<\/p>\n\n\n\n

The LO module requires contact sensors mounted on the legs of the robot. However, for platforms lacking these sensors, we provide a dedicated contact estimation module.<\/p>\n\n\n\n

Results<\/h4>\n\n\n\n

Our results show good performance in terms of localization, mapping, navigation, and exploration in simulated environments.<\/p>\n\n\n\n

\n
\"\"<\/figure>\n\n\n\n
\"\"<\/figure>\n<\/figure>\n\n\n\n

We also validated our mapping results in the real world, including extremely cluttered environments such as the lab at PUT:<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

And we were still able to achieve good mapping results, particularly if compared with the baselines:<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

Our system allows quadruped robots to explore autonomously complex environment withouth too many issues:<\/p>\n\n\n\n

More info<\/h4>\n\n\n\n

If you are interested in knowing more about this project, take a look at<\/p>\n\n\n\n