Amortized Inference for Efficient Grasp Model Adaptation

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.

Authors

• Michael Noseworthy
• Seiji Shaw
• Chad C. Kessens
• Nicholas Roy

Keywords

• Geometry
• Adaptation models
• Uncertainty
• Computational modeling
• Grasping
• Predictive models
• Robustness
• Efficient Adaptation
• Heuristic
• Dynamic Properties
• Friction Coefficient
• Representation Of Uncertainty
• Posterior Probability
• Center Of Mass
• Kinetic Parameters
• Unknown Parameters
• Point Cloud
• Latent Space
• Random Strategy
• Object Properties
• Reward Function
• Particle Filter
• Network Inference
• Feasibility Of Model
• Adaptation Phase
• Fraction Of The Cost
• Robust Behavior
• Unknown Properties
• Belief Updating
• Object Geometry
• Single Time Step
• Evidence Lower Bound
• Information Gain
• Local Cloud
• Test Phase
• Task Format
• Graphical Model