@yxyang1995 Profile picture

Yuxiang Yang

@yxyang1995

PhD student @uwcse on robotics and reinforcement learning, former AI resident @GoogleAI. Walking robot dogs all the time.

Similar User
Chenhao Li photo

@breadli428

Jacky Liang photo

@jackyliang42

Ankit Goyal photo

@imankitgoyal

Nima Fazeli photo

@NimaFazeli7

Dhruv Shah photo

@shahdhruv_

Wenhao Yu photo

@Stacormed

Vikash Kumar photo

@Vikashplus

Harry Zhang photo

@HarryZhangOG

Yuzhe Qin photo

@QinYuzhe

Jiafei Duan photo

@DJiafei

Lin Shao photo

@linshaonju

Roberto photo

@RobobertoMM

Ruihan Yang photo

@RchalYang

Mohit Shridhar photo

@mohito1905

Jason Peng photo

@xbpeng4

Yuxiang Yang Reposted

We have fully open-sourced LocoMan, including hardware files in SolidWorks format, and code for both simulation and deployment. github.com/linchangyi1/Lo…

LocoMan = Quadrupedal Robot + 2 * Loco-Manipulator Powered by dual lightweight 3-DoF Loco-Manipulators and the Whole-Body Controller, LocoMan achieves various challenging tasks, such as manipulation in narrow spaces and bimanual-manipulation. linchangyi1.github.io/LocoMan 👇👇👇



Yuxiang Yang Reposted

Smooth behaviors is vital for successful sim2real transfer of RL policies. This is often achieved with smoothness rewards or low-pass filters, which are not easily differentiable and tend to require tedious tuning. We introduce Lipschitz-Constrained Policies (LCP), a simple and…


Yuxiang Yang Reposted

🎉 Diffusion-style annealing + sampling-based MPC can surpass RL, and seamlessly adapt to task parameters, all 𝘁𝗿𝗮𝗶𝗻𝗶𝗻𝗴-𝗳𝗿𝗲𝗲! We open sourced DIAL-MPC, the first training-free method for whole-body torque control using full-order dynamics 🧵 lecar-lab.github.io/dial-mpc/


Yuxiang Yang Reposted

Agile Continuous Jumping in Discontinuous Terrains discuss: huggingface.co/papers/2409.10… We focus on agile, continuous, and terrain-adaptive jumping of quadrupedal robots in discontinuous terrains such as stairs and stepping stones. Unlike single-step jumping, continuous jumping…


Yuxiang Yang Reposted

🚗🧵Introducing HOUND: an open-source, low-cost research platform for high-speed off-road driving that makes off-road autonomy more accessible to researchers. Paper: arxiv.org/pdf/2311.11199 Website: sites.google.com/view/prl-hound #Robotics #RSS2024


Loading...

Something went wrong.


Something went wrong.