CMU Robotics Institute

Excited to present our work "SuperMap: A Spatio-Temporal SLAM System for Visual-Language Navigation" at RSS 2026! SuperMap is a living spatial memory for embodied AI — it perceives the world, remembers its evolution, and supports reasoning and action. Perceive → Remember → Reason → Act 🌍 Project Page: superodometry.com/supermap #RSS2026 #Robotics #SLAM #EmbodiedAI #SpatialAI #CMURobotics

1/ Progress in robot locomotion scaled with simulation, but touch was left behind. Our work, Tactile Genesis, unlocks sim for dexterous manipulation. Using sim to ablate tactile types and models, we can quickly converge to better tactile hardware and force-informed policies.

Carnegie Mellon University's Robotics Innovation Center officially welcomed global technology company @FujitsuOfficial as its latest corporate tenant in the university’s robotics and artificial intelligence research facility at Hazelwood Green. cmu.edu/news/stories/a…

RIO, a new framework from CMU, provides a unified interface for robot control, data collection, teleoperation and AI deployment! It gives researchers a lightweight, modular foundation for deploying robots quickly on any platform. ri.cmu.edu/robot-io/

1/ Inference-time policy steering lets robots imagine possible futures and pick the best one—but what if the best-looking future still feels wrong? In ViTaL, we argue that for contact-rich tasks, steering robots by using visual futures 👁️ 🌍 is not enough. Robots should also verify what they expect to feel 🤚🌍 as a result of their actions.

A CMU robotics team arrived in Venezuela this week to assist search and rescue crews following two devastating earthquakes. Snake robots designed by CMU’s Biorobotics Lab can squeeze into tight spaces. A camera on the front of the robot can help direct the search for survivors.

Over the weekend, CMU robots took to the stage at the #America250 PA concert! 🇺🇸🎶🤖 We enjoyed showcasing the innovation that fuels our city and our country forward! @SCSatCMU @CMU_Robotics

How can we get robot hands to “hear” slip and contact through microphones, and react to them? We’re excited to share VibeAct, an approach that uses piezoelectric microphones embedded in robot fingertips to estimate contact and slip, then learns reactive policies from this tactile feedback! vibeact.github.io

Residents from a Baptist Senior Family living community visited Zackory Erickson’s Robotic Caregiving & Human Interaction Lab! RCHI works closely with the residents to test their assistive robots. It was a unique opportunity for them to see live demos & meet the students! 😄

Introducing Modality Forcing, a recipe for post-training T2I models for SOTA RGB-Depth generation! Text-to-image (T2I) models learn rich representations of the spatial world. How do we build on this prior for high-quality depth generation? modality-forcing.github.io 🧵 [1/6]

Video world model imaginations🌎💭can miss critical but plausible outcomes of robot actions. Introducing 𝙎𝙩𝙧𝙚𝙨𝙨𝘿𝙧𝙚𝙖𝙢: inference-time steering for video WMs, imagining plausible✅, high-impact⚠️ futures for 𝙧𝙤𝙗𝙪𝙨𝙩🛡️ policy evaluation and improvement. (1/15)

Autoresearch just left the sandbox and entered the embodied world. We are excited to introduce 𝐄𝐍𝐏𝐈𝐑𝐄: a system that drops frontier coding agents onto a fleet of real robots and hands them the entire loop: reset the environment → search the literature → implement ideas and build the infra → train and deploy → self-verify → analyze the logs and rewrite the code → repeat, until the policy is reliable in the real world. No human in the loop. Guided only by the robot's self-proposed, heuristic-based success signal, the agents hill-climb to 99% on dexterous real-world tasks: organizing pins into a box, seating GPUs, tying zip-ties. We envision the bottleneck in robotics shifting — from building smarter algorithms to building the closed physical feedback loops an agent can finally turn on its own. 🔗 research.nvidia.com/labs/gear/enpi… From @NVIDIA @CMU_Robotics @Berkeley_AI 🧵

VideoManip could eliminate the need for robot demonstrations or specialized motion-capture systems, making it easier for robots to learn how to use everyday objects! 🦾📺 #CMUrobotics This is cool stuff, folks ➡️ ri.cmu.edu/cmu-researcher…

So excited to share 𝚆𝙴𝙰𝚅𝙴𝚁 🌎, co-led with @arnavkj95 ! World models are becoming a powerful tool for robot learning — but for real robots, they need to be more than visually realistic. They also need to be consistent, efficient, and useful for decision-making. 🤖✨

The CMU Fire Blighters designed an autonomous navigation robot that moves through orchard rows, detects fire blight symptoms + maps infected trees in real time. 🍎🗺️ They earned the Amiga Innovation Award at the 2026 Farm Robotics Challenge! #TartanProud ri.cmu.edu/carnegie-mello…

💥Introducing FACTR 2, learning external force sensing on commodity robot arms without needing dedicated sensors. We show that learned force signals enable force-feedback teleop on low-cost arms and improve BC policies. FACTR 2 consists of: 1. Neural External Torque (NEXT): learns external forces without needing dedicated force sensors. 2. Force-Informed Re-Sampling Training (FIRST): uses the learned force signal to identify task-critical regions and upsample them during training. w/ @StevenOh_ @_tonytao_ 🧵(1/N)

Two years ago we released VQAScore with a simple idea: ask a VLM "does this image show {prompt}?" and use P(Yes) as the score. It has since become the go-to evaluation metric and reward model for visual generation, replacing CLIPScore across the field. Adopted by Google DeepMind (Imagen 3 & 4), NVIDIA, ByteDance, and other frontier labs. Our open-source model has 2M+ downloads on HuggingFace. Today: a major upgrade. VQAScore now supports text-to-video evaluation using 20+ SOTA VLMs including GPT, Gemini, and Qwen, capturing generation accuracy for prompts like "a shallow depth of field shot rack focusing from a foreground crumpet to a dog entering the background, catching it at the focus shift." As VLMs get stronger, VQAScore gets stronger. For free. 📄 Paper: arxiv.org/abs/2404.01291 💻 Code: github.com/linzhiqiu/t2v_… Thanks to @chancharikm for driving this upgrade, and @gneubig and @RamananDeva.

Congratulations, Deepak! 👏 Learn more about the award and Deepak's work at CMU and beyond: ri.cmu.edu/pathak-receive…

We had amazing Robotics Institute representation at #ICRA2026 in Vienna and #CVPR2026 Denver! 🤖⚙️ Congratulations to all on their hard work! 💪 #TartanProud #CMUrobotics

Apply for the Foundations of Robotic Interactions online graduate certificate program! Next Start Date: August 2026 ⚡ Priority Deadline – June 10, 2026 ✅ Final Deadline – July 29, 2026 Learn more: cmu.edu/online/foundat…