Shibo Profile
Shibo

@ShiboZhaoSLAM

Followers
174
Following
15
Media
5
Statuses
36

RI PhD student at CMU

Joined June 2020
Don't wanna be here? Send us removal request.
@SciRobotics
Science Robotics
2 days
A new Science #Robotics study describes a fusion #odometry system that can adapt to diverse environments and deteriorating conditions, enabling a robot to navigate dense, smoke-filled surroundings. @AirLabCMU @ShiboZhaoSLAM @smash0190 https://t.co/JMGJ7MlzZC
0
2
1
@carlo_sferrazza
Carlo Sferrazza
13 days
Sim-to-real learning for humanoid robots is a full-stack problem. Today, Amazon FAR is releasing a full-stack solution: Holosoma. To accelerate research, we are open-sourcing a complete codebase covering multiple simulation backends, training, retargeting, and real-world
19
131
572
@AjdDavison
Andrew Davison
2 months
If you have an Apple Vision Pro, try the Alive app to see nature in your own room. It was built by Jack during his individual project at Imperial @ICComputing and is now available on the App Store.
@jack_finnis
Jack Finnis
2 months
🚀 Introducing Alive - a unique interactive AR experience for Apple Vision Pro. Bring your living room to life with realistic creatures that react to your gestures, movement, and surroundings in real-time. #AppleVisionPro #VisionPro #SpatialComputing #visionOS #AR @Apple
2
6
60
@fdellaert
Frank Dellaert
2 months
GaussGym looks amazing!
@alescontrela
Alejandro Escontrela
2 months
Simulation drives robotics progress, but how do we close the reality gap? Introducing GaussGym: an open-source framework for learning locomotion from pixels with ultra-fast parallelized photorealistic rendering across >4,000 iPhone, GrandTour, ARKit, and Veo scenes! Thread 🧵
1
1
10
@_ayoungk
Ayoung
3 months
We also release some LaTeX sty and bib files used in the handbook. If you are writing an ICRA paper on SLAM, these should be useful. Visit our GitHub repo for details: https://t.co/HWffjGuz7B
Tweet card summary image
github.com
Release repo for our SLAM Handbook. Contribute to SLAM-Handbook-contributors/slam-handbook-public-release development by creating an account on GitHub.
@lucacarlone1
Luca Carlone
3 months
We have completed the SLAM Handbook "From Localization and Mapping to Spatial Intelligence" and released it online: https://t.co/AnKa398nyw . The handbook will be published by Cambridge University Press. [1/n]
0
6
35
@fdellaert
Frank Dellaert
3 months
We have completed editing the SLAM Handbook "From Localization and Mapping to Spatial Intelligence" and released it. The 3-part handbook will be published by Cambridge University Press. Enjoy reading online for now!
6
23
211
@ShiboZhaoSLAM
Shibo
7 months
(4/n) Big thanks to my collaborators: Honghao Zhu, Yuanjun Gao, Tianhao Wu, Damanpreet Singh, Wenshan Wang, Chen Wang, and Sebastian Scherer. We’d love your feedback — let’s make SLAM evaluation more meaningful!
0
0
1
@ShiboZhaoSLAM
Shibo
7 months
(2/n) 🔧 Key Features: No thresholds required Balances accuracy and completeness Clean mathematical formulation and easy to compute
0
0
1
@ShiboZhaoSLAM
Shibo
7 months
(1/n) Despite years of progress, there is still no widely accepted metric for evaluating SLAM robustness. To bridge this gap, we introduce a new robustness metric that integrates the concept of the F1 score into Relative Pose Error (RPE) calculations.
0
0
1
@ShiboZhaoSLAM
Shibo
7 months
📢 Rethinking SLAM Evaluation ATE has been the standard SLAM metric for years, but it overemphasizes accuracy and ignores trajectory completeness—a key factor in real-world robustness.
4
12
50
@ShiboZhaoSLAM
Shibo
7 months
(3/n) 🙏 Huge thanks to my amazing collaborators: Honghao Zhu, Lucas Nogueira, Hengrui (Henry) Zhang, Yuanjun Gao, Peng Wang, Beomsoo Kim, Yuheng Qiu, Aaron Johnson, and Sebastian Scherer.
0
0
0
@ShiboZhaoSLAM
Shibo
7 months
(2/n) 💡Actively fuse sensors only when necessary The result is a lightweight, robust enhancement that significantly improves localization reliability in degraded environments.
0
0
0
@ShiboZhaoSLAM
Shibo
7 months
(1/n) SuperLoc addresses a critical but often overlooked challenge in LiDAR-inertial odometry: geometric degeneracy. Instead of reacting to failures after they occur, we follow two simple but effective principles: 💡Predict alignment risk at the frontend
0
0
0
@ShiboZhaoSLAM
Shibo
7 months
Excited to share that I will be presenting our latest work, SuperLoc, at #ICRA2025 in Atlanta this week! 🗓 Presentation: May 22 (Thu), 11:25–11:30 AM 📍 Room: 405 (ThCT17.3: Localization 6) 📍 Project: https://t.co/qbSrLHpN7L
3
0
5
@Napoolar
Thomas Fel
1 year
🎭Recent work shows that models’ inductive biases for 'simpler' features may lead to shortcut learning. What do 'simple' vs 'complex' features look like? What roles do they play in generalization? Our new paper explores these questions. https://t.co/aW2PrlYQF4 #Neurips2024
7
105
505
@QiuYuhengQiu
Yuheng Qiu
11 months
Acknowledge all the collaborator @aero_gjy @smash0190 @cannnnxu @YutianChen03 @ShiboZhaoSLAM Our work is powered by Rerun @rerundotio for visualization, and Pypose for EKF integration @pypose_org @DrChenWang.
0
3
7
@zhenjun_zhao
Zhenjun Zhao
11 months
Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video Xiaohao Xu, @tianyiz2022, @ShiboZhaoSLAM, Xiang Li, Sibo Wang, Yongqi Chen, Ye Li, Bhiksha Raj, Matthew Johnson-Roberson, @smash0190, @SeanXiaonan https://t.co/Sma3dxJEc0
1
4
35
@Saboo_Shubham_
Shubham Saboo
11 months
AI Software Engineering Agent using Deepseek R1 that can reason before writing code. It achieves similar performance as OpenAI o1 and Claude Sonnet 3.5 at a fraction of cost. 100% Opensource. https://t.co/vjRHp2ALAK
19
96
770
@ShiboZhaoSLAM
Shibo
1 year
Deeply honored to contribute one chapter with incredible teams for our SLAM Handbook. It has been an invaluable learning experience to collaborate with all the distinguished authors and I am truly grateful for their guidance. Appreciate for any suggestion to make book better!🎉
@lucacarlone1
Luca Carlone
1 year
Pre-release of part 1 of our handbook: from SLAM to Spatial Intelligence. Please provide comments and suggestions to make it better! and a big THANK YOU to our amazing contributors! #spatialAI #robotics #perception #slam #ComputerVision
0
0
1