Learning a State Estimator for Tactile In-Hand Manipulation
Lennart Röstel,Leon Sievers,Johannes Pitz,Berthold Bäuml,Lennart Röstel,Leon Sievers,Johannes Pitz,Berthold Bäuml
We study the problem of estimating the pose of an object which is being manipulated by a multi-fingered robotic hand by only using proprioceptive feedback. To address this challenging problem, we propose a novel variant of differentiable particle filters, which combines two key extensions. First, our learned proposal distribution incorporates recent measurements in a way that mitigates weight dege...
