Shuijing Liu
@dafeijing
Followers
128
Following
75
Media
7
Statuses
26
Postdoc @UTAustin, PhD @UIUC in Robotics, HRI, and ML
Urbana, IL
Joined April 2017
What a fun and rewarding experience at #RSSPioneers2025! Special thanks to the organizers and sponsors!.
Hope you have an enjoyable start of the @RoboticsSciSys 2025! .On behalf of the organizing committee, we'd like to thank everyone for their contributions to the #RSSPioneers2025 workshop! We hope that it was an unforgettable and inspiring experience for our Pioneers!
0
0
4
If you’re attending RSS in LA, feel free to check out my RSS Pioneers lightening talk (~11:30-11:35am) and/or poster session! .I'll share my past work and future vision on robot learning for and from human interactions. @RSSPioneers @RoboticsSciSys @ECEILLINOIS @texas_robotics
1
1
7
📢 Checkout our recent work Casper👻, a VLM-powered assistive robot!.This work is also a meaningful milestone as my first postdoc project.
Meet Casper👻, a friendly robot sidekick who shadows your day, decodes your intents on the fly, and lends a hand while you stay in control! . Instead of passively receiving commands, what if a robot actively sense what you need in the background, and step in when confident? (1/n)
0
0
6
This upcoming week, I'll be at ICRA (Mon-Fri) to present 1 RA-L paper, 1 ICRA paper, and 4 workshop papers. Looking forward to connect to old and new colleagues in Atlanta!
0
1
29
Excited and honored to share that I’m selected as an RSS pioneer! Huge thanks to my colleagues and the organizers who made this possible! If you’re also attending RSS in LA, I’d be happy to connect.
List of 33 #RSSPioneer2025 is out! Their research interests cover fundamental robot design, modelling and control, robot perception and learning, localisation and mapping, human-robot interaction, healthcare and medical robotics, and soft robots! .
0
0
10
Very interesting topic, organized by multiple colleagues of mine. Please check it out!.
Excited to organize Workshop on Learning Meets Model-Based Methods for Contact-Rich Manipulation @ ICRA 2025!. We welcome submissions on a range of topics—check out our website for details:. Join us for an incredible lineup of speakers! #ICRA2025
0
0
0
Please checkout our ICLR 2025 workshop on human-AI co-evolution!.
Excited to announce the ICLR 2025 Workshop on Human-AI Coevolution with @aiprof_mykel, @Diyi_Yang, @sanmikoyejo, David Hsu & more!. #AI #HumanAIInteraction #ICLR2025 #AIResearch #EthicalAI #HCI
0
0
4
RT @SteveTod1998: Excited to share that we’re organizing the Generative Models for Robot Learning workshop at #ICLR2025!. Join us and submi….
0
7
0
Please checkout our ICLR 2025 workshop on human-AI co-evolution! Any kind of participation is welcome!.
🚀 ICLR 2025 workshop on Human-AI Coevolution open for submissions 🚀. Excited to announce our workshop at the International Conference on Learning Representations (ICLR) 2025, bringing together a rapidly growing interdisciplinary community including Mykel Kochenderfer, Yang
0
0
3
RT @kiwi_sherbet: Humans, regardless of arm size or handedness, can fasten screws with the same tool: a screwdriver. What if robots could s….
0
30
0
See our paper + website for details:.📄: 🌐: Special thanks to my collaborators: Haochen Xia, Fatemeh Cheraghi Pouria, @serend1p1ty_x, Neeloy Chakraborty, @callmektbot, and colleagues at HCA Lab! (5/5).@CSL_Illinois @ECEILLINOIS.
0
2
3
In simulation and real world experiments, HEIGHT allows the robot to adapt different strategies to avoid collisions with humans and static obstacles. HEIGHT can zero-shot generalize to changes in the room layout and density of pedestrians. (4/5)
1
0
1
Step 2: We represent each part in the graph with a module, and connect all modules to derive HEIGHT network. Trained with deep RL, HEIGHT learns a policy for the robot to navigate in crowded and constrained environments in a safe and efficient manner. (3/5)
1
0
0
Our recipe:. Step 1: We convert the navigation scenario with a robot, many pedestrians, and obstacles into a spatio-temporal graph. The graph effectively decomposes the complex navigation scenario into smaller parts, which are easier to model and conquer. (2/5)
1
0
0
🤖Want a robot to walk through people in your office? . Introducing HEIGHT🗻: A structured framework for robot navigation in crowded and constrained environments, powered by a graph network that reasons about various interactions. 👇(1/5)
3
8
48
RT @SteveTod1998: How can we scale up humanoid data acquisition with minimal human effort?.Introducing DexMimicGen, a large-scale automated….
0
65
0
RT @huihan_liu: With the recent progress in large-scale multi-task robot training, how can we advance the real-world deployment of multi-ta….
0
47
0
RT @SISLaboratory: Excited for our proposed ICLR 2025 workshop on human-AI co-evolution! We're looking for diverse voices from academia & i….
0
4
0
RT @rutavms: 🤖 Want your robot to grab you a drink from the kitchen downstairs?. 🚀 Introducing BUMBLE: a framework to solve building-wide m….
0
37
0