Indoor environments contain many linear features. We can exploit this structure to extract stable, lightweight features, to develop fast, accurate, and robust SLAM systems
Perceptual systems gain efficiency when they can re-use intermediate results for different inference tasks. Combining Infallible Classification and HAC, we can get multi-level inference, and perform causal analysis between hierarchy levels.
Have you ever had to play through an entire ROS bag file just to find the half dozen frames where your robot did something wrong? What if you could just load your log in a database, give it an example, and let it find all the relevant data....
Opponent Modeling has been a field of interest for a long time. However, as more systems begin operating in continuous domains, we need a critical look at the body of data-driven OM work.
Robots and other AI systems often use MDPs to decide which actions to take. However, specifying the proper reward function is both difficult and rarely ....
I can post here when the product launches.
Check out this great video
Copyright © 2019 Samer Nashed - All Rights Reserved.