🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

We are excited to share our #CORL2024 paper on learning quadrotor obstacle avoidance from the visual stream of a single #eventcamera! Trained entirely in simulation! We demonstrate obstacle avoidance both in the dark and in a forest up to 5m/s. PDF: arxiv.org/pdf/2411.03303 Video:

Are you trying to learn a policy with #ReinforcementLearning from raw image pixels, but it takes too long to train, or it even fails? Reinforcement Learning (RL) from raw image pixels is challenging due to the inefficiency of policy exploration stemming from high-dimensional

Join us this Thursday, December 5th, for a mind-blowing dive into planetary exploration where no machine has gone before! Our guest, Jeff Delaune from NASA JPL, will give a public talk on Robotics Challenges for Planetary Exploration (Mars, Titan, Venus, Enceladus), moon rovers,

Exciting news for Switzerland and Zurich. OpenAI is reportedly opening an office in Zurich "to work on multimodal AI, artificial intelligence models capable of performing tasks in different mediums ranging from images to audio." wired.com/story/openai-h… UZH IfI University of Zurich

We are excited to share our latest work on downwash modeling for drones, published in IEEE Robotics and Automation Letters! PDF: rpg.ifi.uzh.ch/docs/RAL24_Bau… Video: youtu.be/-erfmxWTzPs We present a computationally efficient model for estimating the far-field airflow caused by

We are excited to share our #RAL2025 paper "Drift-free Visual SLAM using Digital Twins"! We remove drift in #VSLAM by aligning the sparse 3D point cloud from VSLAM to a Digital Twin using point-to-plane matching; no visual data association is needed! The result? Accurate,

We are excited to announce the fifth international workshop on Event-based Vision, which will take place during #CVPR2025! More info will be shared soon. Paper submission deadline is March 12. Stay tuned! If you are new to event-based vision, remember that you can find all

We have a professorship opening in Responsible and Trustworthy AI in our department (tenured track assistant, associate, or full professor) in areas like Human-AI interaction, AI and System Design, Explainability, and Societal/Ethical impact and more: ifi.uzh.ch/en/department/…

We are excited to share our #ICLR2025 paper "Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory," which dives into the fundamental theoretical barriers faced by current Deep Learning architectures, such as Structured State Space Models (SSMs). PDF:

I am sharing a tutorial on event cameras that I gave a few months ago at the 2024 Int. Conf. on Computational Photography: youtu.be/0wGBpgIrd9M Below, you will find additional resources on event cameras, such as source codes, datasets, simulators, drivers, courses, and

We are excited to share our #ICLR2025 spotlight paper "Student-Informed Teacher Training," which addresses the teacher-student asymmetry in imitation learning, i.e., when the teacher has access to privileged information about the environment and task while the student only

On March 13, at #WorldMinds2025, in the Kaufleuten Theater of Zurich, our team demonstrated for the first time two autonomous vision-based racing drones. It was an epic journey to prepare for this event, given the poor lighting conditions and the safety constraints of a theater

Meet us this week at #ICLR2025 in Singapore! We will present several papers on #RobotLearning and #MachineLearning at the main conference and workshops! Complete list with times, rooms, and links to PDFs, Code, and Videos at: docs.google.com/document/d/1Hm… With Jiaxu Xing,

I am happy to share that beginning last month I started as Distinguished Visiting Scientist on-site at NASA JPL, where I am having the privilege to collaborate with amazing researchers and engineers on different ambitious projects focused on vision-based navigation for autonomous

Meet us this week at #ICRA2025 in Atlanta! We will present several papers on #RobotLearning, #RobotVision, #FluidDynamics, and #SLAM at the main conference and workshops! Complete list with times, rooms, and links to PDFs, Code, and Videos at: docs.google.com/document/d/1ce… With