Shivam Singhal

TL;DR: In this article, the authors examine the problem of desk organization: learning how humans spatially position different objects on a planar surface according to organizational preference, by examining how humans position objects given multiple features received from vision and haptic modalities.

TL;DR: A model is constructed by fine-tuning Google's Universal Sentence Encoder using a Deep Neural Network and the embedding layer will be allowed to retrain through backpropagation on the Sentiment dataset.

TL;DR: This work demonstrates an imitation learning based approach to train deep visuomotor policies for a variety of manipulation tasks with a simulated five fingered dexterous hand, and finds that using touch sensing information enables faster learning and better asymptotic performance for tasks with high degree of occlusions.

TL;DR: This work examines the problem of desk organization: learning how humans spatially position different objects on a planar surface according to organizational “preference”, and uses two types of models: random forests, which focus on precise multi-task classification, and Markov logic networks, which provide an easily interpretable insight into organizational habits.