SCoTT: Strategic Chain-of-Thought Tasking for Wireless-Aware Robot Navigation in Digital Twins

Path planning under wireless performance constraints is a complex challenge. However, naively incorporating such constraints into classical algorithms often incurs prohibitive search costs. We propose SCoTT, a wireless-aware path planning framework that leverages vision-language models (VLMs) to co-optimize average path gains and trajectory length using wireless heatmaps and ray tracing data from a digital twin (DT). At its core is Strategic Chain-of-Thought Tasking (SCoTT), a novel prompting paradigm that decomposes the exhaustive search problem into manageable subtasks. As baselines, we compare A* and wireless-aware extensions of it, and derive DP-WA*, an optimal dynamic programming algorithm. In extensive experiments, we show that SCoTT achieves path gains within 2% of DP-WA* while consistently generating shorter trajectories. Moreover, SCoTT’s intermediate outputs can be used to accelerate DP-WA* by reducing its search space, saving up to 62% in execution time. We validate SCoTT using four VLMs, demonstrating effectiveness across large and small models, making it applicable to compact VLMs at low inference cost. We also show its practical viability by deploying SCoTT as a ROS node within Gazebo simulations.. Finally, we discuss data-acquisition pipelines, compute requirements, and deployment considerations in 6G-enabled DTs.