Arthur King Zhang (@ArthurKZhang) header
Arthur King Zhang (@ArthurKZhang) profile picture

CS PhD student @UTAustin | Previously @UMRobotics | Love what you do ✌️

Joined May 2019
Photo by Arthur King Zhang (@ArthurKZhang)Photo by Arthur King Zhang (@ArthurKZhang)Photo by Arthur King Zhang (@ArthurKZhang)Photo by Arthur King Zhang (@ArthurKZhang)Photo by Arthur King Zhang (@ArthurKZhang)Photo by Arthur King Zhang (@ArthurKZhang)Photo by Arthur King Zhang (@ArthurKZhang)Photo by Arthur King Zhang (@ArthurKZhang)Photo by Arthur King Zhang (@ArthurKZhang)Photo by Arthur King Zhang (@ArthurKZhang)
🗺️ Scalable mapless navigation demands open-world generalization. Meet CREStE: our SOTA navigation model that nails path planning in novel scenes with just 3 hours of data, navigating 2 Km with just 1 human intervention. Project Page 🌐: amrl.cs.utexas.edu/creste A thread 🧵
2
6
2
22
4,415
What can different navigation domains (e.g. offroad, AV, humanoid, aerial, quadruped, digital) learn from each other? 🎉 Excited to announce the Workshop on “Bridging Perspectives in Navigation” @ IROS 2026 (Pittsburgh, 9/27/2026). Submit your paper by August 21! 👇
1
4
1
8
1,131
Can robots learn to navigate by repurposing the visual priors inside image diffusion models? Introducing Ventura: adapting image diffusion models to ground language commands to executable motion plans. Presenting @ ICRA 9-10:30 AM Tuesday Paper TuI1I.299. More in this 🧵(1/6)
1
2
4
258
To learn more about Ventura, check out our website for open-source code, pre-trained models, and additional cool robot videos! (5/6) Project Website: venturapath.github.io Code: github.com/artzha/ventura_pu…
1
62
Thank you to my collaborators @fieldai_ and @amrl_ut for making this work possible! (6/6) Luca Calliari, Xiangyun Meng, Dong-Ki Kim, Shayegan Omidshafiei, @Joydeepb_robots , Ali Agha, Amirreza Shaban1
39
Arthur King Zhang retweeted
How can robots follow complex instructions in dynamic environments? 🤖 Meet ComposableNav — a diffusion-based planner that enables robots to generate novel navigation behaviors that satisfy diverse instruction specifications on the fly — no retraining needed. 📄 Just accepted to CoRL 2025 🔗 Project: amrl.cs.utexas.edu/Composabl… A Thread (1/8)
1
7
2
19
2,780
Interested in deploying real robots in open-world, outdoor environments? Come to our presentation this Tuesday at 9:30AM, poster #12 @USC to learn how we master outdoor navigation with internet scale data and human-in-the-loop feedback! #RSS2025 @RoboticsSciSys
🗺️ Scalable mapless navigation demands open-world generalization. Meet CREStE: our SOTA navigation model that nails path planning in novel scenes with just 3 hours of data, navigating 2 Km with just 1 human intervention. Project Page 🌐: amrl.cs.utexas.edu/creste A thread 🧵
3
9
1,384
(6/n) To test open-world generalization, we deploy CREStE on a 2 km mission in an unseen urban loop, intervening only to provide high level directional guidance. Our approach adapts to unseen environments, rare dynamic entities, and challenging scenes with little room for error. youtu.be/OzcYNURwjJQ?si=dZzg…
1
1
137
(7/n) This work was accepted at @RoboticsSciSys 2025! Come say hi at our poster session during the @ieee_ras_icra SafeVLMs workshop on May 23rd. Lastly, I want to thank my amazing collaborators @harshit_sikchi, @yayitsamyzhang, and @Joydeepb_robots for their help and guidance in making this remarkable work possible! @amrl_ut @lab_midi @UTAustin @texas_robotics
1
2
235
I am thrilled to announce that UT CODa has been accepted at #IeeeTro24! Thank you to all of my collaborators at @Joydeepb_robots @amrl_ut who helped make this work possible. We are also excited to share the release of CODa version 2. More on CODa v2 in this🧵
3
2
1
12
1,452
ReMEmbR by @_abraranwar and the Nvidia team leverage CODa to perform long-form video question answering for robot navigation. Project Website: nvidia-ai-iot.github.io/reme…
1
3
4
257
If you’re interested in using CODa, please check our website and visit our interactive poster at #ICRA40 on Tuesday from 12:30-1:15 PM at booth TuINTS1.7! Project Website (CODa_v2 available for download here): amrl.cs.utexas.edu/coda/
1
1
171