MIT

In December 2025, pillars of the robotics community faced difficult times, industry leaders took new positions, and some new robot releases. 

A team of MIT researchers created a speech-to-reality system that enables a robot to build furniture with just a simple request.

Miniaturization offers robotics designers new levels of power efficiency, nimbleness, and precision for a range of applications.

An international group of roboticists, including three from MIT, debated the best way to approach robotic manipulation moving forward.

In July, The Robot Report launched a new program geared toward highlighting unique and interesting startups.

MIT CSAIL said the main barrier to affordable, flexible robotics isn’t hardware, it’s control of capability.

MIT researchers have developed the E-BAR system to assist older adults in safe movement around the household.

In her keynote, MIT CSAIL Director Daniela Rus will discuss the challenges of transformer-based foundation AI models.

The joint research team from MIT and Notre Dame created the Soft Pathfinding Robotic Observation Unit, or SPROUT.

A low-power system using radio frequency waves takes a step toward autonomous, indoor drone navigation

MIT engineers developed a robotic replica of the heart’s right ventricle that mimics its beating and blood-pumping action of live hearts.

Inspired by large language models, researchers develop a training technique that pools diverse data to teach robots new skills.

The Mars Oxygen In-Situ Resource Utilization Experiment, or MOXIE, generated oxygen aboard NASA’s Perseverance Rover.

When paired with real-world data, the RialTo system created at MIT CSAIL outperformed traditional imitation learning methods.

A new surgical procedure gives people more neural feedback from their residual limb. With it, seven patients walked more naturally and navigated obstacles.

Robotic manipulation and teleoperation have advanced in the past few years, but researchers at MIT and UC San Diego have developed Open-TeleVision to overcome limitations.

RoboGrocery uses soft robotics, sensors, and algorithms to handle a stream of unpredictable objects on a conveyor belt, said MIT CSAIL.

MIT AI experts have applied a deep-learning model that can decongest robots nearly four times faster than typical strong random search methods. 

MIT CSAIL’s research examines the economic practicality of using AI for automating tasks, with a particular emphasis on computer vision.

A multimodal system uses models trained on language, vision, and action data to help robots develop and execute plans for household, construction, and manufacturing tasks.

Project Ddog aims to turn a Boston Dynamics Spot quadruped into a basic communicator for those with physical challenges such as ALS. 

Universal Robots had strong attendance at its U.S. headquarters open house, which featured presentations, demonstrations, and networking.