Amortized Inference for Efficient Grasp Model Adaptation

Michael Noseworthy, Seiji A Shaw, Chad Kessens, Nicholas Roy

Abstract:

In robotic applications such as bin-picking or
block-stacking, learned predictive models have been developed
for manipulation of objects with varying but known dynamic
properties (e.g., mass distributions and friction coefficients).
When a robot encounters a new object, these properties
are often difficult to observe and must be inferred through
interaction, which can be expensive in both inference time
and number of interactions. We propose an encoder/decoder
action-feasibility model to efficiently adapt to new objects by
estimating their unobserved properties through interaction. The
encoder predicts a distribution over the unobserved parameters
while the decoder predicts action feasibility, which can be used
in an uncertainty-aware planner. An explicit representation
of uncertainty in the encoder enables information-gathering
heuristics to minimize adaptation interactions. The amortized
distributions are efficient to compute and perform comparably
to particle-based distributions in a grasping domain. Finally, we
deploy our method on a Panda robot to grasp heavy objects.