4 accepted papers
Offline policy improvement faces an inherent conflict between maximizing value and fitting the data distribution. While in-sample weighted regression is stable, it suffers from over-conservatism that suppresses high-value actions in the distribution tail; conversely, gradient-based approaches often …
In this letter, we present the design, manufacturing, and performance test of a centimeter-scale two-legged swimming robot, RoboNotonecta, inspired by the efficient and agile locomotion of an aquatic beetle backswimmer (Notonectid). The robot utilizes a crank-slider and slider-rocker paddling mechan
This letter presents the design, fabrication, and performance test of a fish-like underwater miniature robot directly driven by two piezoelectric actuators. Considering the different medium conditions and the ever-present challenge of waterproofing in underwater motion, the miniaturization of underw
Multi-modal flapping robots demonstrate potential capabilities to accomplish assigned missions in confined indoor and outdoor environments. In this letter, inspired by the multimodal movement of insects, we report a multimodal tailless flapping wing robot capable of flying, crawling, self-righting a