We present IndoorSim-to-OutdoorReal (I2O), an end-to-end learned visual
...
We present Visual Navigation and Locomotion over obstacles (ViNL), which...
If we want to train robots in simulation before deploying them in realit...
Deep reinforcement learning models are notoriously data hungry, yet
real...
Navigation policies are commonly learned on idealized cylinder agents in...
We study the challenging problem of releasing a robot in a previously un...
Does progress in simulation translate to progress in robotics? Specifica...