Sparse Closed-form Liquid Neural Algorithms for Out-of-Distribution Generalization on Edge Robots

According to one aspect, a system includes an autonomous agent and a sparse closed-form network. The autonomous agent has one or more cameras configured to receive images of an environment in which the agent is operating, one or more motors, and a controller configured to command the motors to move the agent with desired velocities. The sparse closed-form network is configured to process the images to determine the desired velocities for navigating the agent to a target.

Researchers

Daniela Rus / Makram Chahine / Mathias Lechner / Ramin Hasani / Alexander Amini

Departments: Dept of Electrical Engineering & Computer Science, Computer Science & Artificial Intelligence Lab
Technology Areas: Artificial Intelligence (AI) and Machine Learning (ML) / Computer Science: Bioinformatics / Industrial Engineering & Automation: Robotics

  • sparse closed-form liquid neural algorithms for out-of-distribution generalization on edge robots
    United States of America | Pending

License this technology

Interested in this technology? Connect with our experienced licensing team to initiate the process.

Sign up for technology updates

Sign up now to receive the latest updates on cutting-edge technologies and innovations.