Modified 2017-11-23 by Adrien Ali Taiga
Modified 2017-11-23 by Adrien Ali Taiga
Modified 2017-11-23 by Adrien Ali Taiga
Build a map from a duckie driving around the road autonomously that will be used for planning
Modified 2017-11-23 by Adrien Ali Taiga
À l’idiot sans mémoire tout lui paraît nouveau et miraculeux
Modified 2017-11-23 by Adrien Ali Taiga
What is in scope
Train agent to learn to explore an entire map efficiently and leep a representation of the current knowledge of the map.
What is out of scope
Need to run live on the duckie. We do not use real images but assume we have a tile detector
Stakeholders
Transfer learning team - tbd
Modified 2017-11-23 by Adrien Ali Taiga
Modified 2017-11-23 by Adrien Ali Taiga
We want the to keep a representation of the current map in memory that could used for downstream task such as planning
Modified 2017-11-23 by Adrien Ali Taiga
Modified 2017-11-23 by Adrien Ali Taiga
Stage 0: Create an environment where we can a simulated agent
Stage 1: Train an agent using a reinforcement learning method paired with an external memory
Stage 2: Deploy on the real robot and see how the method perform
Stage 3: Use a decoder that can recover the knowledge of the map
Modified 2017-11-23 by Adrien Ali Taiga
Modified 2017-11-23 by Adrien Ali Taiga
Modified 2017-11-23 by Adrien Ali Taiga
Modified 2017-11-23 by Adrien Ali Taiga
Modified 2017-11-23 by Adrien Ali Taiga
Modified 2017-11-23 by Adrien Ali Taiga
Modified 2017-11-23 by Adrien Ali Taiga
Simulator
Policy network
Decoder
Modified 2017-11-23 by Adrien Ali Taiga
Modified 2017-11-23 by Adrien Ali Taiga
No need to revise duckietown specifications
Modified 2017-11-23 by Adrien Ali Taiga
Modified 2017-11-23 by Adrien Ali Taiga
Modified 2017-11-23 by Adrien Ali Taiga
Modified 2017-11-23 by Adrien Ali Taiga
Modified 2017-11-23 by Adrien Ali Taiga
Duckietown simulator
Modified 2017-11-23 by Adrien Ali Taiga
No questions found. You can ask a question on the website.