Kazuki Mizuta

Multi-robot systems offer significant advantages for autonomously exploring large-scale, unknown environments. A critical challenge in these applications, however, is ensuring the safety of all agents in a scalable and efficient manner, especially when operating with decentralized coordination and limited communication. To overcome this limitation, this article presents a fully distributed algorithm that enables a multi-robot team to explore cooperatively while maintaining formal safety guarantees. The core of our approach is a framework where each robot individually trains a sparse Bayesian classifier using its local LiDAR data to probabilistically model unsafe regions. To achieve collaborative awareness, the robots exchange these compact, learned models, not high-volume raw data, and fuse them to construct a shared safety map. Safety is then formally guaranteed through a control barrier function (CBF) derived from this collaborative map. The effectiveness of the proposed algorithm are validated through both simulations and experiments with physical ground robots.

Signal Temporal Logic (STL) offers a concise yet expressive framework for specifying and reasoning about spatio-temporal behaviors of robotic systems. Attractively, STL admits the notion of robustness, the degree to which an input signal satisfies or violates an STL specification, thus providing a nuanced evaluation of system performance. In particular, the differentiability of STL robustness enables direct integration to robotic workflows that rely on gradient-based optimization, such as trajectory optimization and deep learning. However, existing approaches to evaluating and differentiating STL robustness rely on recurrent computations, which become inefficient with longer sequences, limiting their use in time-sensitive applications. In this letter, we present STLCG++, a masking-based approach that parallelizes STL robustness evaluation and backpropagation across timesteps, achieving significant speed-ups compared to a recurrent approach. We also introduce a smoothing technique to enable the differentiation of time interval bounds, thereby expanding STL's applicability in gradient-based optimization tasks involving spatial and temporal variables. Finally, we demonstrate STLCG++’s benefits through three robotics use cases and provide JAX and PyTorch libraries for seamless integration into modern robotics workflows.