Robot Videos: Multimodal Robot, Spot's Strong Arm, More

Video Friday is your weekly selection of awesome robotics videos, collected by your friends at IEEE Spectrum robotics. We also post a weekly calendar of upcoming robotics events for the next few months. Please send us your events for inclusion.

IROS 2025: 19–25 October 2025, HANGZHOU, CHINA

Enjoy today’s videos!

Caltech’s Center for Autonomous Systems and Technologies (CAST) and the Technology Innovation Institute in Abu Dhabi, UAE, recently conducted a demonstration of X1, a multirobot system developed as part of a three-year collaboration between the two institutes. During the demo, M4, a multimodal robot developed by CAST, launches in drone mode from a humanoid robot’s back. It lands and converts into driving mode and then back again, as needed. The demonstration underscored the kind of progress that is possible when engineers from multiple institutions at the forefront of autonomous systems and technologies truly collaborate.

[ Caltech Center for Autonomous Systems and Technologies ]

Spot performs dynamic whole-body manipulation using a combination of reinforcement learning and sampling-based control. Behavior shown in the video is fully autonomous, including the dynamic selection of contacts on the arm, legs, and body, and coordination between the manipulation and locomotion processes. The tire weighs 15 kilograms (33 pounds), making its mass and inertial energy significant compared to the weight of the robot. An external motion-capture system was used to simplify perception, and an external computer linked by Wi-Fi performed the intensive computational operations.

Spot’s arm is stronger than I thought. Also, the arm-foot collaboration is pretty wild.

[ Robotics and AI Institute ]

Figure 03 represents an unprecedented advancement in taking humanoid robots from experimental prototypes to deployable, scalable products. By uniting advanced perception and tactile intelligence with home-safe design and mass-manufacturing readiness, Figure has built a platform capable of learning, adapting, and working across both domestic and commercial settings. Designed for Helix, the home, and the world at scale, Figure 03 establishes the foundation for true general-purpose robotics, one capable of transforming how people live and work.

The kid and the dog in those clips make me very, very nervous.

[ Figure ]

Researchers have invented a new superagile robot that can cleverly change shape thanks to amorphous characteristics akin to the popular Marvel antihero Venom. Researchers used a special material called electro-morphing gel (e-MG) which allows the robots to show shape-shifting functions, allowing them to bend, stretch, and move in ways that were previously difficult or impossible, through manipulation of electric fields from ultralightweight electrodes.

[ University of Bristol ]

This is very preliminary of course, but I love the idea of quadrupedal robots physically assisting each other to surmount obstacles like this.

[ Robot Perception and Learning Lab ]

Have we reached peak dynamic humanoid yet?

[ Unitree ]

Dynamic manipulation, such as robots tossing or throwing objects, has recently gained attention as a novel paradigm to speed up logistic operations. However, the focus has predominantly been on the object’s landing location, irrespective of its final orientation. In this work, we present a method enabling a robot to accurately “throw-flip” objects to a desired landing pose (position and orientation).

[ LASA ]

I don’t care all that much about “industry-oriented” quadrupeds. I do care very much about “ridable” quadrupeds.

[ MagicLab ]

I am not yet at the point where I would trust any humanoid around priceless ancient relics. Any humanoid, not just the robotic ones.

[ LimX ]

This Carnegie Mellon University RI Seminar, “A Manipulation Journey,” is presented by Matt Mason, professor emeritus at CMU.

The talk will revisit my career in manipulation research, focusing on projects that might offer some useful lessons for others. We will start with my beginnings at the MIT AI Lab and my MS thesis, which is still my most-cited work, then continue with my arrival at CMU, a discussion with Allen Newell, an exercise to envision a coherent research program, and how that led to a second and third childhood. The talk will conclude with some discussion of lessons learned.

[ Carnegie Mellon University Robotics Institute ]