∇SLAM: Dense SLAM meets Automatic Differentiation

gradslam

gradslam is an open-source framework providing differentiable building blocks for simultaneous localization and mapping (SLAM) systems. We enable the usage of dense SLAM subsystems from the comfort of PyTorch.

People

Krishna Murthy Jatavallabhula

    Krishna Murthy Jatavallabhula



Advisor: Liam Paull    
Thesis: Differentiable world programs
Current Position: PostDoc at MIT with Antonio Torralba and Joshua Tenenbaum
Liam Paull

    Liam Paull



Interests: Robot perception, uncertainty, sim2real, and robot benchmarking

Department of Computer Science and Operations Research | Université de Montréal | Mila