🔥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

👇Introducing DPPO, Diffusion Policy Policy Optimization DPPO optimizes pre-trained Diffusion Policy using policy gradient from RL, showing 𝘀𝘂𝗿𝗽𝗿𝗶𝘀𝗶𝗻𝗴 𝗶𝗺𝗽𝗿𝗼𝘃𝗲𝗺𝗲𝗻𝘁𝘀 over a variety of baselines across benchmarks and sim2real transfer diffusion-ppo.github.io

Accepted to #CoRL2024: our work on calibrated uncertainty quantification for perception systems for end-to-end statistical assurances for navigation! Perceive with Confidence: arxiv.org/abs/2403.08185 Work led by Anushri Dixit during her postdoc at Princeton University!

Uncertainty quantification is a big missing piece of the puzzle in robotics. Very excited to be organizing a workshop at #RSS2025 with Lars Lindemann and Anastasios Nikolas Angelopoulos! We have a stellar cast of speakers and panelists from academia and industry to discuss the role and

Attending #ICLR2025 next week! I will be presenting Diffusion Policy Policy Optimization (DPPO) at the Friday morning poster session with Lars Ankile diffusion-ppo.github.io I also joined Physical Intelligence lately. Love to chat about what we've been up to at Pi!

What a memorable way to wrap up my PhD: I had the privilege of presenting my work on safe human-centered robotics at the GRASP SFI seminar series Penn Engineering Huge thanks to the GRASP Laboratory for inviting me and to everyone who attended! youtube.com/watch?v=50ZId5…

Introducing Human-Centered Safety Filter (HCSF) to be presented at #RSS2025! Can robot co-pilots keep us safe while preserving human agency? 💡We propose an HCSF for complex shared autonomy like car racing. Project page: safe-racing.github.io Arxiv: lnkd.in/gtgDYNN5

arxiv.org/pdf/2505.00779 Uncertainty-aware Latent Safety Filters for Avoiding OOD Failures using world model's epistemic uncertainty as a proxy for potential ood hazards, calibrating with CP, then do reachability analysis with uncertainty and latent space

Extremely honored to be part of this year’s RSS Pioneers cohort! Looking forward to meeting everyone in LA!

Want your imitation learning policy to generalize better, but how to collect data to achieve this? 🤖🤔 Enter Factored Scaling Curves (FSC): a tool that quantifies how policy success scales with demos for each environmental factor, enabling principled data collection 📈 . 🌐

World models help scale safe control to extremely complex systems, but they introduce their own set of challenges. Check out Junwon’s uncertainty-aware latent safety filters that help us deal with hallucinating world models!

Do reasoning language models 𝒌𝒏𝒐𝒘 𝒘𝒉𝒆𝒏 𝒕𝒉𝒆𝒚 𝒅𝒐𝒏'𝒕 𝒌𝒏𝒐𝒘? Or does deeper reasoning lead to models becoming even more confidently wrong? 🤔 Check out our new paper to find some answers! arxiv.org/abs/2506.18183