While there are many potential uses for soft-bodied robots, the things are still typically only built in small experimental batches. Scottish scientists are out to change that, with a mass-production-capable soft bot that is 3D-printed in a single piece which then walks off of the print bed.

Before we go any further, this isn’t the first time we’ve heard about a soft robot that was printed in one piece.

It was just this March that we told you about a hexapod bot created at UC San Diego, which was 3D-printed in one continuous 58-hour step. That robot was powered not by a motor but by compressed air, which sequentially moves its legs forward.

There’s a deep human desire to know, to better understand the world, and for decision-makers within organizations to do that in a way that’s grounded in data and grounded in fact.

Humans excel at performing complex tasks by leveraging long-term memory across temporal and spatial experiences. In contrast, current Large Language Models (LLMs) struggle to effectively plan and act in dynamic, multi-room 3D environments. We posit that part of this limitation is due to the lack of proper 3D spatial-temporal memory modeling in LLMs. To address this, we first introduce 3DMem-Bench, a comprehensive benchmark comprising over 26,000 trajectories and 2,892 embodied tasks, question-answering and captioning, designed to evaluate an agent’s ability to reason over long-term memory in 3D environments. Second, we propose 3DLLM-Mem, a novel dynamic memory management and fusion model for embodied spatial-temporal reasoning and actions in LLMs.