Abstract:Limbless locomotors, from microscopic worms to macroscopic snakes, traverse complex, heterogeneous natural environments typically using undulatory body wave propagation. Theoretical and robophysical models typically emphasize body kinematics and active neural/electronic control. However, we contend that because such approaches often neglect the role of passive, mechanically controlled processes (i.e., those involving mechanical intelligence), they fail to reproduce the performance of even the simplest organisms. To discover principles of how mechanical intelligence aids limbless locomotion in heterogeneous terradynamic regimes, here we conduct a comparative study of locomotion in a model of heterogeneous terrain (lattices of rigid posts). We use a model biological system, the highly studied nematode worm C. elegans, and a novel robophysical device whose bilateral actuator morphology models that of limbless organisms across scales. The robot's kinematics quantitatively reproduce the performance of the nematodes with purely open-loop control; mechanical intelligence simplifies control of obstacle navigation and exploitation by reducing the need for active sensing and feedback. An active behavior observed in C. elegans, undulatory wave reversal upon head collisions, robustifies locomotion via exploitation of the systems' mechanical intelligence. Our study provides insights into how neurally simple limbless organisms like nematodes can leverage mechanical intelligence via appropriately tuned bilateral actuation to locomote in complex environments. These principles likely apply to neurally more sophisticated organisms and also provide a new design and control paradigm for limbless robots for applications like search and rescue and planetary exploration.
Abstract:Inference efficiency is the predominant consideration in designing deep learning accelerators. Previous work mainly focuses on skipping zero values to deal with remarkable ineffectual computation, while zero bits in non-zero values, as another major source of ineffectual computation, is often ignored. The reason lies on the difficulty of extracting essential bits during operating multiply-and-accumulate (MAC) in the processing element. Based on the fact that zero bits occupy as high as 68.9% fraction in the overall weights of modern deep convolutional neural network models, this paper firstly proposes a weight kneading technique that could eliminate ineffectual computation caused by either zero value weights or zero bits in non-zero weights, simultaneously. Besides, a split-and-accumulate (SAC) computing pattern in replacement of conventional MAC, as well as the corresponding hardware accelerator design called Tetris are proposed to support weight kneading at the hardware level. Experimental results prove that Tetris could speed up inference up to 1.50x, and improve power efficiency up to 5.33x compared with the state-of-the-art baselines.