FANGWEN YU

How to represent robot’s pose with a rate-coded neural network CAN in RatSLAM?

The excerpt note is about robot’s pose representation with a rate-coded neural network, continuous attractor network (CAN) in RatSLAM from Michael and Gordon 2010.

The CAN is a neural network that consists of an array of units with fixed weighted …

Be the First to comment. Read More

How to perform Path Integration in RatSLAM?

The excerpt note is about path integration in RatSLAM from Michael et al. 2010, 2008, 2004.

The RatSLAM system uses poses cells to concurrently represent the beliefs about the location and orientation of the robot. By representing in the same …

Be the First to comment. Read More

How does the velocity take effects on movement of activity of Pose Cells in RatSLAM?

The excerpt note is about how to move the activity of pose cells according to the translational and rotational velocity in RatSLAM from Michael et al. 2008, 2004.

The new path integration method shifts existing pose cell activity rather than

Be the First to comment. Read More

How to update the activity of pose cells in RatSLAM?

The excerpt note is from Michael et al., 2008, which explains the detail process to update the activity of pose cells in RatSLAM.

Milford, Michael J., and Gordon F. Wyeth. “Mapping a suburb with a single camera using a

Be the First to comment. Read More

How to build robust, visual-inertial state estimation for autonomous navigation?

Robust, Visual-Inertial State Estimation: from Frame-based to Event-based Cameras

This lecture was presented by Professor Davide Scaramuzza at Affiliation University of Zurich, ETH Zurich in September 25, 2017 on Series Microsoft Research Talks.

Professor Davide Scaramuzza presented main algorithms to …

Be the First to comment. Read More

Why drones can learn to navigate autonomously by imitating cars and bicycles?

Drones learn to navigate autonomously by imitating cars and bicycles powered by AI

January 23, 2018, by University of Zurich

Developed by UZH researchers, the algorithm DroNet allows drones to fly completely by themselves through the streets of a city

Be the First to comment. Read More

How to enable robot cognitive mapping inspired by Grid Cells, Head Direction Cells and Speed Cells?

Taiping Zeng, and Bailu Si. “Cognitive Mapping Based on Conjunctive Representations of Space and Movement.” Frontiers in Neurorobotics 11 (2017).

In this work, the researchers developed a cognitive mapping model for mobile robots, taking advantage of the coding …

Be the First to comment. Read More