A systematic comparative study of the role of touch sensing in dexterous, multi-fingered IL, evaluating three IL algorithms across transformer, Mamba, and xLSTM backbones, and multiple tactile representations, and offering practical insights into the choice of learning algorithm, backbone, and tactile representation.
Niklas Leukroth, Pankhuri Vanjani, J. Suliga et al.· 0 citations
Tactile information is essential for contact-rich manipulation tasks in robotics. Vision-based tactile sensors make it particularly easy to design end-to-end manipulation policies with tactile sensing, as they enable the use of existing encoders from computer vision. However, this has led to a huge variety of architect...
Seongjin Bien, Débora Oliveira Makowski, Carlo Kneissl et al.· arXiv.org· 0 citations
Comparisons within ReCAT show that the observation encoder and every-block memory conditioning are needed for this performance, and that update rules developed for efficient sequence modeling behave differently as robot memory: additive updates have the highest observed success on counting and timing, and delta-rule up...
Pankhuri Vanjani, M. Hatab, Can Mizrakli et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.