Amortized Inference for Efficient Grasp Model Adaptation
Michael Noseworthy,Seiji Shaw,Chad C. Kessens,Nicholas Roy,Michael Noseworthy,Seiji Shaw,Chad C. Kessens,Nicholas Roy
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 inferenc...
