Guide dog robots offer promising solutions to enhance mobility and safety for visually impaired individuals, addressing the limitations of traditional guide dogs, particularly in perceptual intelligence and communication. With the emergence of Vision-Language Models (VLMs), robots are now capable of generating natural language descriptions of their surroundings, aiding in safer decision-making. However, existing VLMs often struggle to accurately interpret and convey spatial relationships, which is crucial for navigation in complex environments such as street crossings. We introduce the Space-Aware Instruction Tuning (SAIT) dataset and the Space-Aware Benchmark (SA-Bench) to address the limitations of current VLMs in understanding physical environments. Our automated data generation pipeline focuses on the virtual path to the destination in 3D space and the surroundings, enhancing environmental comprehension and enabling VLMs to provide more accurate guidance to visually impaired individuals. We also propose an evaluation protocol to assess VLM effectiveness in delivering walking guidance. Comparative experiments demonstrate that our space-aware instruction-tuned model outperforms state-of-the-art algorithms. We have fully open-sourced the SAIT dataset and SA-Bench, along with the related code, at https://github.com/byungokhan/Space-awareVLM

Many quadrupedal robots can adeptly handle uneven or sloped terrain, but only if the ground beneath them is relatively stable. Factor in slippery or muddy surroundings and four-legged machines may quickly falter or fail completely. But one engineering team believes they found a solution in mimicking animals often found in boggy habitats. According to a study published in Bioinspiration & Biomimetics by researchers at Estonia's Tallinn University of Technology (TalTech), dog bots could soon take their cues from giant moose. "[M]ost robots cannot access a wide range of highly important terrestrial environments, including wetlands, bogs, coastal marshes, river estuaries and fields, which are abundant in nature," explained TalTech biorobotics professor and team lead, Maarja Kruusmaa, in an accompanying statement on January 2nd. Ungulates (split-hooved animals like cattle and moose), however, are evolutionarily equipped to handle these often sticky situations.

"Spirit" may one day be part of a pack of robots that become man's best friend on the Moon and Mars.

In this paper, we consider the problem of protecting a high-value area from being breached by sheep agents by crafting motions for dog robots. We use control barrier functions to pose constraints on the dogs' velocities that induce repulsion in the sheep relative to the high-value area. This paper extends the results developed in our prior work on the same topic in three ways. Firstly, we implement and validate our previously developed centralized herding algorithm on many robots. We show herding of up to five sheep agents using three dog robots. Secondly, as an extension to the centralized approach, we develop two distributed herding algorithms, one favoring feasibility while the other favoring optimality. In the first algorithm, we allocate a unique sheep to a unique dog, making that dog responsible for herding its allocated sheep away from the protected zone. We provide feasibility proof for this approach, along with numerical simulations. In the second algorithm, we develop an iterative distributed reformulation of the centralized algorithm, which inherits the optimality (i.e. budget efficiency) from the centralized approach. Lastly, we conduct real-world experiments of these distributed algorithms and demonstrate herding of up to five sheep agents using five dog robots.

Welcome to the world of delivery robots: one of the fastest-growing and most competitive markets in robotics. The idea behind these bots is simple: The customer orders an item, that item is loaded into or onto the robot, and then the robot travels to the customer to drop it off. But that's not stopped multiple intrepid companies from exploring their own innovative approaches to the challenge. Here are six of the biggest names to watch out for when it comes to delivery robots. With its Star Trek-sounding name, it's no surprise that Starship went boldly where no other robotics company has gone before; helping invent the modern delivery robot in the process.

When you think of canine-inspired robots, your brain probably conjures up images of Boston Dynamics' celebrated dog robot, Spot. Swiss robotics company Anybotics has also created its own audacious, quadruped robot. The size of a large dog and weighing a little under 80 pounds, Anymal aims to be the gold standard in dog-bots. It's capable of autonomously walking, running, and climbing, and can even get back on its feet if it falls over. Although Spot will go on sale for the first time later this year, this gleaming robotic beast is already on the market in Europe, the United States, and the Middle East.