Intelligent Control Lab
@ICL_at_CMU
Followers
49
Following
7
Media
4
Statuses
26
Intelligent Control Lab in the Robotics Institute at Carnegie Mellon University.
Joined February 2024
RT @huhanjiang: Just as humans transitioned from understanding nature to controlling it, can we move beyond just solving PDEs to actually c….
0
1
0
6/n.💡 We were also the only team to run in fully autonomous mode in the packing track during the competition!. Huge thanks to the amazing team that made this possible! 🙌 @PeiqiYu1019 @RuixuanLiu_ . Read more at:
icontrol.ri.cmu.edu
0
0
2
5/n.✅ Data efficiency—perception models were adapted with just one hour of retraining on a RTX 4060 laptop; skills are learned through one-shot key frame demonstrations. ✅ High reliability, achieving a >90% task success rate.
1
0
1
4/n.This hybrid approach enabled:.✅ Strong generalization across tasks (e.g., object types) and embodiments (e.g., robotic platforms and sensor configurations)—we trained on Unitree G1 and only accessed the competition setup 3 days before the event;.
1
0
1
3/n.🔹 Human knowledge for intuitive priors (e.g., “stacked bowls should be grasped from the interior”).🔹 Assured and robust model-based robotics techniques, including fast motion planning and safe control.
1
0
1
2/n.We developed a neuro-symbolic framework—called Skill Graph—that strategically decomposes the manipulation problem to leverage the best-suited method for each component:.🔹 Data-driven models for complex perception.
1
0
1
1/n.🎉 Exciting news from #ICRA2025! The student team from the Intelligent Control Lab won First Prize ($60k) in the Packing Track of the What Bimanual Teleoperation and Learning from Demonstration Can Do (WBCD) competition! 🏆
1
1
3
🎉 Congrats to Prof Changliu Liu @ChangliuL on IEEE RAS Early Academic Career Award in Robotics and Automation "for significant advancements in intelligent robot control and learning that enables safe and efficient human-robot collaborations"! @CMU_Robotics #ICRA2025
0
4
11
🚀 The Intelligent Control Lab is heading to #ICRA2025!. Our team will be presenting a range of exciting research next week—come check it out!. 🔗 Full list of talks and posters:
0
1
5
RT @huhanjiang: 🔐 Can we ensure AI safety through the lens of safe control?. 💥 We model the multi-turn LLM conversation as a neural dialogu….
0
6
0
RT @TairanHe99: 🚀 Can we make a humanoid move like Cristiano Ronaldo, LeBron James and Kobe Byrant?. YES!. 🤖 Introducing ASAP: Aligning Sim….
0
199
0
🚀 Our work is featured in the latest @ARM_Robotics article on the Digital Framework for Sustainment & Maintenance! 🎯🔧. Check out how our innovation is shaping the future of digital sustainment: 🔗 #AI #Robotics #ManufacturingInnovation.
arminstitute.org
Read the lastest post from the ARM Institute - Project Highlight: Digital Framework for Sustainment and Maintenance
0
2
3
RT @Li_liangzhii: 🤖Can highly nonlinear legged robots be controlled by simple linear controller? .🌟Yes—with Incremental Koopman! . Our Incr….
0
4
0
💡 Excited to share new work from our lab! 🎉 SPARK (Safe Protective & Assistive Robot Kit) is set to redefine safety in humanoid robotics. 🤖. A big step towards ensuring seamless and provably safe human-robot interaction!. Learn more here: . Stay tuned!.
[1/4] 🌟Sneak Peek: SPARK in Action! 🦾.Previewing Safe Protective & Assistive Robot Kit (SPARK)—a modular toolbox designed to enhance safety in humanoid autonomy and teleoperation. Safety isn't just a feature—it's the foundation for humanoids to truly integrate into human life.
0
0
2
We also have two papers accepted at SAFE-ROL workshop on Sat,.🔹 Estimating Neural Network Robustness via Lipschitz Constant and Architecture Sensitivity, led by Abulikemu Abuduweili.🔹 Verification of Neural Control Barrier Functions with Symbolic Derivative Bounds Propagation.
0
0
1
🔹 KOROL: Learning Visualizable Object Feature with Koopman Operator Rollout for Manipulation, led by @chen_hongyi_ .🗓️ Session 3, Thu 4:00 PM.📐 Our Koopman-based approach brings math-interpretable features to robot manipulation. Video & code:
1
0
1
🔹 OmniH2O: Universal Human-to-Humanoid Whole-Body Teleoperation, led by @TairanHe99 .🗓️ Session 3, Thu 4:00 PM.🤖 OmniH2O enables real-time control and autonomy for humanoids across diverse tasks—from sports to interaction with humans. Website:
1
0
2
🔹 Verification of Neural Control Barrier Functions with Symbolic Derivative Bounds Propagation, led by @huhanjiang .🗓️ Session 2, Thu 11:00 AM.💻 Our framework verifies neural CBFs with tight, efficient bounds to guarantee safe robot control. Code:
1
0
1
🔹 Meta-Control: Automatic Model-based Control Synthesis for Heterogeneous Robot Skills, led by @wei_tianhao .🗓️Session 2, Thu 11:00 AM.🚀 We leverage LLMs to automate the control design process for diverse robot tasks. Explore more:
1
0
1
Excited to share our latest research at #CoRL2024! Our lab presents breakthroughs in LLM-based control synthesis, safety verification, humanoid teleoperation, Koopman-based manipulation and Lipschitz-based robustness. Check out the threads below for highlights from each paper!👇.
1
0
1