Generating realistic human motion from given action descriptions has experienced significant advancements because of the emerging requirement of digital humans. While recent works have achieved impressive results in generating motion directly from textual action descriptions, they often support only a single modality of the control signal, which limits their application in the real digital human industry. This paper presents a Motion General-Purpose generaTor (MotionGPT) that can use multimodal control signals, e.g., text and single-frame poses, for generating consecutive human motions by treating multimodal signals as special input tokens in large language models (LLMs). Specifically, we first quantize multimodal control signals into discrete codes and then formulate them in a unified prompt instruction to ask the LLMs to generate the motion answer. Our MotionGPT demonstrates a unified human motion generation model with multimodal control signals by tuning a mere 0.4% of LLM parameters. To the best of our knowledge, MotionGPT is the first method to generate human motion by multimodal control signals, which we hope can shed light on this new direction. Codes shall be released upon acceptance.

Within 10 minutes of its birth, a baby fawn is able to stand. Within seven hours, it is able to walk. Between those two milestones, it engages in a highly adorable, highly frenetic flailing of limbs to figure it all out. While autonomous robots, like self-driving cars, are already a familiar concept, autonomously learning robots are still just an aspiration. Existing reinforcement-learning algorithms that allow robots to learn movements through trial and error still rely heavily on human intervention.

People who walk backwards perform better in a memory test than those who stand still or walk forward, a study has found. Researchers asked 114 volunteers to watch a video in which a woman had her bag stolen and then answer a questionnaire about what they could recall. After watching the video, participants were split into groups - one was told to walk forwards or backwards 30 feet (10m) while a control group stood in one place. They were then asked twenty questions about the events in the video and it was found that the backward-walking group got two more answers correct on average than the forward-walkers and the non-walkers. People who walk backwards perform better in a memory test than those who stand still or walk forward, a study has found.

A new design tool could soon allow'just about anybody' to build their own custom robotic pets. Scientists have developed a drag-and-drop interface that provides users with a library of different parts, and even makes suggestions as to how certain components should be used. So far, researchers have used it to create all kinds of machines, from a wheeled robot with a knack for drawing to a four-legged puppy-bot, and they say it can be mastered by experts and novices alike. Scientists have developed a drag-and-drop interface that provides users with a library of different parts. According to the researchers, the system works with off-the-shelf brackets and 3D printable parts. With the interface, users can drag robotic parts, such as a leg or a motor, and place it onto the design.

Using a familiar drag-and-drop interface, individuals can choose from a library of components and place them into the design. The tool suggests components that are compatible with each other, offers potential placements of actuators and can automatically generate structural components to connect those actuators. Once the design is complete, the tool provides a physical simulation environment to test the robot before fabricating it, enabling users to iteratively adjust the design to achieve a desired look or motion. "The process of creating new robotic systems today is notoriously challenging, time-consuming and resource-intensive," said Stelian Coros, assistant professor of robotics. "In the not-so-distant future, however, robots will be part of the fabric of daily life and more people -- not just roboticists -- will want to customize robots. This type of interactive design tool would make this possible for just about anybody."

If Hollywood ever had a lesson for scientists it is what happens if machines start to rebel against their human creators. Yet despite this, roboticists have started to teach their own creations to say no to human orders. They have programmed a pair of diminutive humanoid robots called Shafer and Dempster to disobey instructions from humans if it puts their own safety at risk. Robotics engineers are developing robots that can disobey instructions from humans if they believe it may cause them to become damaged. If asked to walk forward on a table top (pictured) the robot replies that it can't do this as it is'unsafe'.