Heng Yang @hankyang94 Twitter profile | Pikagi

Pikagi

Heng Yang

@hankyang94

3,961

Followers

556

Following

45

Media

273

Statuses

Assistant Professor @Harvard SEAS @hseas , Director of the Harvard Computational Robotics Lab. #Robotics , #Vision , #Control , #Optimization , #Learning

Cambridge, MA

https://t.co/dnxGeGIdUK

Joined January 2017

Don't wanna be here? Send us removal request.

Pinned Tweet

@hankyang94

Heng Yang

4 months

Cannot be more excited about my PhD student @ShuchengK 's new work after spending his first year diving into moment and sums of squares relaxations. Fast and Certifiable Trajectory Optimization We have seen so many pendulum swing-ups, but I bet you haven't seen this one: - The

4

24

181

Last Seen Profiles

@sac4nagem

@GA_Primary

@OzzAndy1

@OzzAndy1

@qkftkd

@bokeplokalmalam

@SomaYoshinori

@itirafet_korkma

@MonTerrassa

@_katiearchibald

@dregizmo

@cukienaknikmati

@apitsumi_main

@Wisawa015

@MonTerrassa

@2KANG01

@ToadJunkie

@Felupus

@TogariV_

@kttyp0wer

@nel71070

@bpa58

@setagayafes_tcu

@nubzombie

@Nadia_Nadaan

@fastshop

@abihangikanal

@marin_chiba2

@itsmygreylife

@gxthkirumi

@jealousjoey444

@powenvan

@marin_chiba2

@TY72517486

@benhNFTs

@Putinhocps

@hankyang94

Heng Yang

2 years

Grad school applicants: my Computational Robotics group at Harvard SEAS is hiring PhD students in Fall 2023! If you are interested in robotics, computer vision, machine learning, applied math, and their application in safe autonomy, you are the person I am looking for!

27

126

519

@hankyang94

Heng Yang

2 years

I'll join @Harvard as an Assistant Professor of Electrical Engineering in @hseas School of Engineering and Applied Sciences in Fall'23. I'll build a #ComputationalRobotics lab studying the algorithmic foundations of robot perception, action and learning. Contact me if interested!

Tweet media one

23

15

436

@hankyang94

Heng Yang

10 months

Grad school applicants: this year I am particularly looking for a strong candidate in **statistics** and **machine learning** who is also interested in robotics applications. Please apply to Harvard and reach out if you’re interested!

5

69

332

@hankyang94

Heng Yang

7 months

Meet the Harvard Computational Robotics Group!

Tweet media one

5

22

309

@hankyang94

Heng Yang

5 months

Our Harvard Computational Robotics group has - 2 papers accepted to #L4DC2024 - 1 paper accepted to #RAL - 1 paper accepted to #ICML2024 - 1 paper accepted to #RSS2024 80% of these paper were authored by undergrad visitors last summer, who will go to the best PhD programs this

4

15

229

@hankyang94

Heng Yang

3 years

Super excited to share STRIDE, the first algorithm that can solve high-order tight semidefinite relaxations to high accuracy, which are extremely powerful global optimization tools for general polynomial optimizations but notoriously difficult to solve.

Tweet media one

4

37

198

@hankyang94

Heng Yang

2 years

I defended my PhD today! Thank you @lucacarlone1 , Russ, Jean-Jacques, @JustinMSolomon , and @KostasPenn , what a great committee!

Tweet media one

Tweet media two

Tweet media three

9

1

114

@hankyang94

Heng Yang

9 months

What is the true optimal value function of the infinite-horizon inverted pendulum problem? Despite being a simple nonlinear optimal control problem, its optimal value function remains a mystery until @Hyhan0118 uncovered the answer. a thread (1/n)

Tweet media one

1

12

96

@hankyang94

Heng Yang

4 years

It’s such an honor to win the best paper award in robot vision at @icra2020 ! Many thanks go to my co-authors @AntonanteP @VassilisTzoumas and @lucacarlone1 for their amazing feedback in both writing a great paper and doing a great presentation! Video:

Tweet media one

4

4

93

@hankyang94

Heng Yang

2 years

So excited our paper "Certifiably Optimal Outlier-Robust Geometric Perception" is accepted to IEEE TPAMI! It unifies my PhD work in designing tractable geometric estimation algorithms with optimality guarantees, in outlier-contaminated realistic setups.

Tweet media one

3

9

85

@hankyang94

Heng Yang

5 months

We are organizing a Frontiers of Optimization for Robotics workshop in the upcoming Robotics: Science and Systems conference at Netherlands. A great lineup of speakers covering four diverse topics: Geometry & Global Optimality, Speed & Scale, Optimization through Contact, and

Tweet media one

1

8

82

@hankyang94

Heng Yang

5 years

Super excited to share new work “TEASER: Fast and Certifiable Point Cloud Registration” with Jingnan Shi and @lucacarlone1 Paper: Code: TEASER is the first algorithm of its kind in many practical and theoretical aspects:

Tweet media one

@DeepAI

DeepAI

5 years

TEASER: Fast and Certifiable Point Cloud Registration by @hankyang94 et al. #Estimator #OpenSource

0

1

8

2

20

73

@hankyang94

Heng Yang

2 years

Reach out if you’re interested in Autonomous Vehicle research internship at NVIDIA!

@yuewang314

Yue Wang

2 years

Our group () led by @drmapavone is looking for PhD research interns for next year. If you’re excited about 3D deep learning, motion planning, and control for robotics/autonomous driving, please consider applying to our group!

4

23

119

2

11

63

@hankyang94

Heng Yang

3 months

Training deep #ReinforcementLearning agents can be unstable. This instability gets magnified in a Lifelong Learning setup, leading to the intriguing phenomenon called Loss of Plasticity (Negative Transfer), where the agent gradually loses the ability to adapt to new information

@aneeshers

Aneesh Muppidi

3 months

⭐New Paper Alert ⭐ How can your #RL agent quickly adapt to new distribution shifts ? And without ANY tuning?🤔 We suggest you get on the Fast TRAC🏎️💨, our new Parameter-free Optimizer that surprisingly works. Why? Website: 1/🧵

7

21

119

2

8

64

@hankyang94

Heng Yang

2 years

#CVPR2023 highlight paper w/ @drmapavone : We combine #ConformalPrediction , #SetMembershipEstimation , #SemidefiniteRelaxation to perform pose estimation with "provably correct" uncertainty quantification: a worst-case error bound from the groundtruth

3

9

55

@hankyang94

Heng Yang

3 years

Super honored to appear on today's MIT Spotlight! Thank you @MIT for sharing our work on #CertifiablePerception and our vision about a future with safe robots and trustworthy autonomy. I am deeply grateful to @lucacarlone1 for the tremendous support!

Spotlight: Safer autonomous vehicles

4

0

54

@hankyang94

Heng Yang

2 years

Prof. Na Li and I have open #postdoc positions at Harvard SEAS @hseas in #Learning , #Optimization , #Control , and/or #Robotics . Please consider apply and help spread the word!

2

9

53

@hankyang94

Heng Yang

1 year

Proud of @YuXihang (undergrad from UM)’s intern project at Harvard! SIM-Sync, Certifiably Optimal camera trajectory estimation directly from 2D images with learned depth. 2D kpts + learned depth —> scaled point clouds —> sync over 3D similarity group

Tweet media one

3

8

50

@hankyang94

Heng Yang

3 years

#RSS2021 check out - "Optimal Pose and Shape Estimation for Category-level 3D Object Perception" (w/ @jingnanshi , @lucacarlone1 ) in poster session I (ET 11:15AM tmr!) and IV - "Certifiable Outlier-Robust Machine Perception" in the RSS Pioneers poster session 0 (ET 10AM tmr!)

0

4

51

@hankyang94

Heng Yang

1 month

We need more convex optimization

@beenwrekt

Ben Recht

1 month

This semester, I’m back to live blogging my course lectures. I’m teaching Convex Optimization in the Age of LLMs.

7

75

650

2

6

52

@hankyang94

Heng Yang

2 months

"Fast and Certifiable Trajectory Optimization" just got accepted to the International Workshop on the Algorithmic Foundations of Robotics (WAFR) @wafr_conf , great job @ShuchengK !

@hankyang94

Heng Yang

4 months

Cannot be more excited about my PhD student @ShuchengK 's new work after spending his first year diving into moment and sums of squares relaxations. Fast and Certifiable Trajectory Optimization We have seen so many pendulum swing-ups, but I bet you haven't seen this one: - The

4

24

181

2

6

47

@hankyang94

Heng Yang

5 months

Computer vision friends: is there a large-scale structure from motion dataset (e.g., over 2000 frames) whose images are labelled with keypoint correspondences? Was looking at the building Rome in a day dataset but it seems no keypoints are provided.

6

4

45

@hankyang94

Heng Yang

4 years

I have got many questions about how to use TEASER++ for 3D registration in practice. Finally, I wrote a step-by-step tutorial about using FPFH and TEASER++ on the 3DMatch dataset, in our favorite language Python:

1

9

43

@hankyang94

Heng Yang

4 years

Our ICRA 2020 paper on graduated non-convexity for robust spatial perception has been implemented by Matlab navigation toolbox and featured by @MathWorks news! If you haven’t read the paper, here it is:

Tweet card media

New Algorithm Improves Robot Perception

MIT researchers developed the graduated non-convexity (GNC) algorithm, which reduces random errors and uncertainties in SLAM results, resulting in correct mapping compared with common SLAM algorithms.

www.mathworks.com

0

8

39

@hankyang94

Heng Yang

4 years

Self-supervised Geometric Perception, with W. Dong, @lucacarlone1 , V. Koltun, is accepted as #CVPR2021 Oral. Appreciated the discussion w/ @ducha_aiki on difference b/w SGP and reconstruction-based supervised learning. Check out future research on Page 8:

Tweet media one

1

9

38

@hankyang94

Heng Yang

7 months

Presenting "Fast and Certifiable Approximation of Pose Uncertainty Sets" tomorrow at the INFORMS Optimization Society Conference, a series of two works from my group. Given a nonconvex pose uncertainty set (PURSE), how to approximate its minimum enclosing (geodesic) ball with a

Tweet media one

1

4

35

@hankyang94

Heng Yang

4 months

In an era of rapid robotics demos, maybe we should get together in a workshop, revisit some of the “old problems” we used to care about, and ask how do our new methods work on the old problems?

@aneeshers

Aneesh Muppidi

4 months

🧲3/3 The answer: sort of... but not really. Control problems require continuous adjustments for stability, which the diffusion policy, being a less-than-optimal control approximation, could not maintain. Could @ChaoyiPan 's Model-based Diffusion work?

1

0

8

1

3

35

@hankyang94

Heng Yang

11 months

Join me 10am ET 11/21! Super excited to talk about new work on computing the minimum enclosing ellipsoid of set-membership estimation in control and perception, via convex optimization (of course). Examples from system identification and object pose estimation will be presented.

Tweet media one

@GioeleZardini

Gioele Zardini

11 months

Talk 2: Speaker: Prof. @hankyang94 , @Harvard Title: Revisiting the Minimum Enclosing Ellipsoid of Set-Membership Estimation in Control and Perception When? November 21 2023, 16:00 CET Where? #autonomytalks

Tweet media one

0

0

4

0

3

34

@hankyang94

Heng Yang

3 years

In spotting objects amid clutter, how can a machine tell the difference between a success and a failure, and correct its failure, if at all possible? Certifiable Outlier-Robust Geometric Perception, enabling robots to see the world with confidence. Paper:

Tweet media one

2

4

31

@hankyang94

Heng Yang

1 year

Congrats to my incoming PhD student Shucheng Kang on getting his paper accepted to IEEE CDC 2023! I believe this multilevel polynomial optimization formulation has promise beyond verification and synthesis of robust control barrier functions!

Tweet card media

Verification and Synthesis of Robust Control Barrier Functions:...

We study the problem of verification and synthesis of robust control barrier functions (CBF) for control-affine polynomial systems with bounded additive uncertainty and convex polynomial...

0

3

30

@hankyang94

Heng Yang

8 months

The sparse Moment-SOS hierarchy just got even more powerful -- handle unbounded sets! With this, we solve optimal control of the unstable Van der Pol oscillator to certifiable global optimality! Great work led by Lei, @ShuchengK , and Jie!

Tweet media one

3

5

30

@hankyang94

Heng Yang

11 months

Was a busy week but had a lot of fun hosting Jean-Bernard Lasserre at Harvard. Such a nice, energetic, and fun person! I hope the wonton with chili sauce was good :)

Tweet media one

0

1

30

@hankyang94

Heng Yang

4 years

Glad to be a finalist of MIT's first Research SLAM featuring 3-Minute Thesis! What a broad range of cool science! #CertifiablePerception Come join the public showcase at 5PM EDT Monday 29th!

Tweet media one

1

3

31

@hankyang94

Heng Yang

1 year

NVIDIA Autonomous Vehicle Research group resumed hiring! Check out this opportunity if you’re interested in autonomous driving, robotics, foundation models etc.

@yuewang314

Yue Wang

1 year

Our group resumes hiring! If you’re interested in autonomous driving, robotics, foundation models etc, definitely check out this opportunity!

0

2

32

0

1

29

@hankyang94

Heng Yang

4 years

If you are attending #CVPR2020 , check out our paper: In Perfect Shape: Certifiably Optimal 3D Shape Reconstruction From 2D Landmarks. I will be holding two live Q&A sessions in EDT: 1-3PM June 16th, and 1-3AM June 17th (3AM is crazy!) Join me in discussing #CertifiablePerception !

Tweet media one

0

4

29

@hankyang94

Heng Yang

4 years

Our paper "Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejection" has been nominated as Best Paper Award Finalist in Robot Vision at #ICRA2020 . GNC is the new RANSAC, check out the paper here:

Tweet card media

Graduated Non-Convexity for Robust Spatial Perception: From...

Semidefinite Programming (SDP) and Sums-of-Squares (SOS) relaxations have led to certifiably optimal non-minimal solvers for several robotics and computer vision problems. However, most...

1

4

29

@hankyang94

Heng Yang

3 months

At #RSS2024 ? Check out three works from the #HarvardComputationalRobotics lab presented at the main conference and workshops: - CLOSURE: GPU-accelerated fast end-to-end uncertainty quantification for 6D pose estimation, main conference "Perception" session - STROM: Fast and

1

5

28

@hankyang94

Heng Yang

2 years

Excited to share a new preprint: Verification and synthesis of ROBUST control barrier functions for control-affine polynomial systems with bounded state-dependent additive uncertainty and convex polynomial control constraints. Three key techniques👇

Tweet card media

Verification and Synthesis of Robust Control Barrier Functions:...

We study the problem of verification and synthesis of robust control barrier functions (CBF) for control-affine polynomial systems with bounded additive uncertainty and convex polynomial...

1

3

27

@hankyang94

Heng Yang

3 years

@gabrielpeyre This is interesting, I think you will like this similar idea called graduated non-convexity that solves non-convex robust estimation using a sequence of surrogate functions.

0

3

28

@hankyang94

Heng Yang

4 months

With @imZhiyuZ 's expertise in adaptive online learning, we are initiating an exciting research thread in our group "lifelong learning amid distribution shifts" and bridging the theory there to robot learning applications. In our ICML paper, Zhiyu revisited the notion of a

@imZhiyuZ

Zhiyu Zhang

4 months

A short thread about our ICML paper, joint work with David Bombara and Heng Yang ( @hankyang94 ). tldr: Follow the Regularized Leader (FTRL), as a well-known gradient descent replacement in online learning, is particularly useful for lifelong learning and conformal prediction.

Tweet media one

2

7

49

1

5

27

@hankyang94

Heng Yang

4 years

I’d like to share an interesting dynamical perspective on point cloud registration, where Newton-Euler dynamics and Lyapunov theory are adopted to analyze nontrivial convergence under virtual springs and damping. Glad to see F=ma still shines.

Tweet media one

1

6

26

@hankyang94

Heng Yang

10 months

Excited to share the paper with @yukai_tang02 (an amazing undergrad!) and Jean Lasserre on revisiting the computational challenges of minimum enclosing ellipsoids: The presentation I gave at Autonomy Talks:

Tweet card media

Autonomy Talks - Heng Yang: Revisiting the Minimum Enclosing Ellips...

Autonomy Talks - 21/11/23Speaker: Prof. Heng Yang, Harvard UniversityTitle: Revisiting the Minimum Enclosing Ellipsoid of Set-Membership Estimation in Contro...

www.youtube.com

@hankyang94

Heng Yang

11 months

Join me 10am ET 11/21! Super excited to talk about new work on computing the minimum enclosing ellipsoid of set-membership estimation in control and perception, via convex optimization (of course). Examples from system identification and object pose estimation will be presented.

Tweet media one

0

3

34

0

0

25

@hankyang94

Heng Yang

4 years

TEASER is now an accepted paper in Transactions on Robotics! Gratitude goes to coauthors @jingnanshi , @lucacarlone1 , reviewers, and many others who read, tried and gave feedback. Stay tuned for more #CertifiablePerception . Paper: Code:

Tweet card media

GitHub - MIT-SPARK/TEASER-plusplus: A fast and robust point cloud registration library

A fast and robust point cloud registration library - MIT-SPARK/TEASER-plusplus

0

5

25

@hankyang94

Heng Yang

5 years

Graduated Non-Convexity (GNC) is the counterpart for RANSAC: while RANSAC robustifies minimal solvers, GNC robustifies non-minimal solvers. The intriguing duality for robust estimation: {Consensus Maximization, Minimal Solver, RANSAC} and {M-estimation, Non minimal Solver, GNC}😀

Tweet media one

@lucacarlone1

Luca Carlone

5 years

GNC is the new RANSAC: our paper on robust perception via Graduated Non-Convexity and non-minimal solvers has been accepted on RA-L! congrats to Yang, Pasquale, and Vasileios #mitSparkLab

0

2

26

0

5

23

@hankyang94

Heng Yang

2 years

Excited to present recent work with @drmapavone that applies conformal prediction to obtain probabilistically correct object pose estimation with uncertainty quantification at ECCV Workshop on 3D Perception for Autonomous Driving. See attached image for a sneak peak!

Tweet media one

@RGiryes

Raja Giryes 💔

2 years

Come and hear @AnguelovDrago , @DengxinD , Deva Ramanan, @kkitani , Junyu Nan, @lucacarlone1 , @AljosaOsep , @orlitany , @KeilafOmer , Jurgen Gall, @hankyang94 and @drmapavone for very interesting talks. The full schedule appears here

1

1

8

2

5

22

@hankyang94

Heng Yang

3 years

It’s a rainy cold day in Boston. But what a warm surprise I got the beautiful #RSSPioneers2021 mug delivered! Very thankful to the wonderful organizers @_krishna_murthy @GeorgiaChal :)

Tweet media one

Tweet media two

2

0

22

@hankyang94

Heng Yang

2 years

Before that, I will be a Research Scientist in the Autonomous Vehicles Research Group @NVIDIAAI led by @MarcoPavoneSU starting July 2022. Deep thanks to all the people who supported me, most importantly, my amazing advisor @lucacarlone1 !

1

1

23

@hankyang94

Heng Yang

3 years

Very excited to give this talk in person! Tune in if you want to hear about certifiable algorithms for robot perception.

@GRASPlab

GRASP Laboratory

3 years

Join us for the [HYBRID] Fall 2021 GRASP Seminar: Heng Yang, Massachusetts Institute of Technology , “Certifiable Outlier-Robust Geometric Perception: Robots that See through the Clutter with Confidence” - This Wednesday (12/15) @ 2:00pm in Levine 307 and via Zoom!

Tweet media one

1

6

31

0

0

23

@hankyang94

Heng Yang

3 years

Our GNC paper got a RAL best paper honorable mention in addition to the ICRA best paper award in robot vision last year! I still remember that day, the four of us looking at the same monitor, polishing the paper WORD by WORD. Good paper really pays back!

Tweet media one

1

0

22

@hankyang94

Heng Yang

1 year

It was wonderful to have @tatjunchin talk about “Quantum Robust Fitting” to my group and visit Harvard SEAS. One of the most fun and educative talks I have heard in a while. I didn’t know Boscovich discovered Earth is oblate using robust fitting!

Tweet media one

Tweet media two

Tweet media three

0

0

22

@hankyang94

Heng Yang

4 years

First time NeurIPS!

@lucacarlone1

Luca Carlone

4 years

2 papers accepted at @NeurIPSConf - one in collaboration with @davsca1 . no bragging, just very proud of the work of my students and collaborators - @hankyang94 , Francesco Milano, @antoniloq , @RosinolToni

1

4

41

2

0

21

@hankyang94

Heng Yang

3 years

Now you have a better reason to visit us because we are one of the best paper finalists! July 14th ET 10AM Session IV :)

@hankyang94

Heng Yang

3 years

#RSS2021 check out - "Optimal Pose and Shape Estimation for Category-level 3D Object Perception" (w/ @jingnanshi , @lucacarlone1 ) in poster session I (ET 11:15AM tmr!) and IV - "Certifiable Outlier-Robust Machine Perception" in the RSS Pioneers poster session 0 (ET 10AM tmr!)

0

4

51

0

2

21

@hankyang94

Heng Yang

2 years

We are organizing an #ACC2023 Workshop on Safe & Robust Learning for **Perception-based Planning and Control**, consider submitting your best work to our workshop👇 deadline May 5th, 2023

Tweet card media

Safe Learning for Perception-based Control

Objectives and Topics: Driven by advances in computer vision (CV) and machine learning (ML), robots have gained the ability to build better world models from high-dimensional sensory feedback (e.g.,...

sites.google.com

0

1

18

@hankyang94

Heng Yang

4 years

Dynamics and Perception? With C. Doran and J.-J. Slotine, we propose DynAMical Pose estimation (DAMP), solving five pose estimation problems by simulating rigid body dynamics from virtual springs and damping: Paper: Video:

Tweet card media

Dynamical Pose Estimation

Dynamical Pose EstimationHeng Yang (MIT), Chris Doran (University of Cambridge), Jean-Jacques Slotine (MIT)Paper: https://arxiv.org/abs/2103.06182Abstract: W...

www.youtube.com

0

3

20

@hankyang94

Heng Yang

3 years

Our RSS'21 work shows (i) Certifiable algorithms can be fast; (ii) Robust estimation is general; (iii) Once you get the math correct, everything should work like a charm even on real nasty data! Check out category-level object pose and shape estimation

Tweet card media

Optimal Pose and Shape Estimation for Category-level 3D Object Perception

We consider a category-level perception problem, where one is given 3D sensor data picturing an object of a given category (e.g. a car), and has to reconstruct the pose and shape of the object...

@lucacarlone1

Luca Carlone

3 years

Traditional approaches for category-level object pose and shape estimation are sensitive to outliers and get stuck in local minima. We propose the first approach that avoids local minima and is robust to 70-90% outliers: #computervision #mitsparklab

2

4

28

0

3

18

@hankyang94

Heng Yang

4 years

With @lucacarlone1 , our work on proposing the first general and practical framework for #CertifiablyRobustPerception has been accepted to #NeurIPS2020 ! Check out the final version: Paper: Code: Video:

Tweet media one

0

2

17

@hankyang94

Heng Yang

10 months

Check out this cool work that combines PAC-Bayes and conformal prediction at #NeurIPS2023 !

@apoorva__sharma

Apoorva Sharma

@apoorva__sharma

10 months

Exciting to be presenting our recent work on PAC-Bayes generalization guarantees for conformal prediction at #NeurIPS23 ! Come by our poster ( #1818 ) on Wednesday at 5pm to chat if you're around. Read on to learn more: 1/6

1

5

8

0

2

16

@hankyang94

Heng Yang

3 years

Sharing the work that I am most proud of: STRIDE for solving rank-one semidefinite relaxation of polynomial optimization. We handle inexactness, prove global convergence, design a modified L-BFGS, and solve important optimization in math and engineering:

Tweet card media

An Inexact Projected Gradient Method with Rounding and Lifting by...

We consider solving high-order semidefinite programming (SDP) relaxations of nonconvex polynomial optimization problems (POPs) that often admit degenerate rank-one optimal solutions. Instead of...

2

4

16

@hankyang94

Heng Yang

3 years

#CVPR2021 Come check out "Self-supervised Geometric Perception" during paper session 11 at 10PM-12:30AM June 24 EDT (tomorrow night), or just have some casual chat!

@hankyang94

Heng Yang

4 years

Self-supervised Geometric Perception, with W. Dong, @lucacarlone1 , V. Koltun, is accepted as #CVPR2021 Oral. Appreciated the discussion w/ @ducha_aiki on difference b/w SGP and reconstruction-based supervised learning. Check out future research on Page 8:

Tweet media one

1

9

38

0

2

16

@hankyang94

Heng Yang

5 months

@antoine_leeman Look out for “Fast and Certifiable Trajectory Optimization” from our group soon :)

2

0

16

@hankyang94

Heng Yang

5 years

With @lucacarlone1 , we present Shape*, the first certifiably optimal non-minimal solver for 3D shape reconstruction from 2D landmarks in a single image, and Shape#, a robust shape reconstruction algorithm that tolerates 70% outliers.

0

5

16

@hankyang94

Heng Yang

3 years

Life winds up in ways we can never expect, the best thing to do is to keep integrating. 10 yrs ago I started college in Tsinghua. In no way I expected my Lorentz cone would lead me to MIT. Hope we all find thrills walking inside (maybe outside) the cone. Happy New Year🎆

0

1

15

@hankyang94

Heng Yang

2 years

Attending #ICRA2022 next week. Can’t believe this will be my FIRST in-person ICRA! Look forward to hearing cool projects and meeting friends, old and new!

0

0

14

@hankyang94

Heng Yang

2 years

Go Harvard SEAS!

@hseas

Harvard SEAS

2 years

SEAS welcomes 10 new faculty. Their areas of expertise include robotics, bioengineering, artificial intelligence, machine learning, and quantum engineering.

3

8

78

0

0

14

@hankyang94

Heng Yang

4 years

Proud of this new preprint that proposes a general framework to design #certifiably robust geometric perception algorithms that are able to decide whether or not outliers have been correctly rejected. I believe that algorithms with guarantees will safeguard robot perception.

@lucacarlone1

Luca Carlone

4 years

New and exciting SPARK preprint: "One Ring to Rule Them All: Certifiably Robust Geometric Perception with Outliers". Kudos to @hankyang94 ! #mitSparkLab #robotperception #computervision #certifiableAlgorithms

1

2

21

0

1

13

@hankyang94

Heng Yang

4 years

I had a lot of fun talking about #CertifiablyRobustPerception with #outliers in both SPARK Lab and Marine Robotics Group at MIT. Today I also had the chance to present to a broader audience at our #RSS2020 tutorial. Check out the video here:

Tweet card media

Certifiably Robust Geometric Perception with Outliers: From TEASER to...

Abstract: Geometric perception, estimating unknown geometric models from visual measurements, is a fundamental problem in computer vision and robotics. Altho...

www.youtube.com

2

3

13

@hankyang94

Heng Yang

4 months

Check out how NVIDIA plans to reshape AV with foundation models!

@drmapavone

Marco Pavone

4 months

At @NVIDIAGTC , I presented my group's strategy on leveraging foundation models (FMs) to develop next-gen autonomous vehicles. Slides: Recording: Three pillars: standing up the FMs, using them within an AV program, and AI safety.

1

29

90

0

0

13

@hankyang94

Heng Yang

2 years

Honda, BD and Agility for sure make cooler humanoids. But Tesla, a public company with a spirit of bravery, promises a $20K humanoid definitely brings unprecedented hope and hype. We need hope and with correct feedback from roboticists perhaps we can do it differently this time.

Tweet media one

2

0

13

@hankyang94

Heng Yang

3 years

👈.T=👆 🤣.T=🤣

0

2

12

@hankyang94

Heng Yang

3 years

Thanks to Wei Dong, a clean and general implementation of "Self-supervised Geometric Perception" [CVPR2021] is now released, with detailed instructions. Try it on 3D registration, camera relative pose estimation, and other problems of interest.

GitHub - theNded/SGP: [CVPR 2021 Oral] Self-supervised Geometric Perception

[CVPR 2021 Oral] Self-supervised Geometric Perception - theNded/SGP

@hankyang94

Heng Yang

4 years

Self-supervised Geometric Perception, with W. Dong, @lucacarlone1 , V. Koltun, is accepted as #CVPR2021 Oral. Appreciated the discussion w/ @ducha_aiki on difference b/w SGP and reconstruction-based supervised learning. Check out future research on Page 8:

Tweet media one

1

9

38

0

4

11

@hankyang94

Heng Yang

2 years

I spent 2+ hours googling how to embed fonts into a pdf on Mac to pass IEEE PDF eXpress check, and none worked ... Feeling desperate, I opened Preview and exported the pdf with "Create PDF/A" and it worked ... just in case you also suffered from this ...

0

0

11

@hankyang94

Heng Yang

4 years

@ducha_aiki @wdong397 @lucacarlone1 @Jimantha Thanks Dmytro for the swift review, hours after we uploaded the paper! The difference between our method SGP and 3D reconstruction-based supervised training has been discussed many times among ourselves, and the difference can be both subtle and deep. Here is my rebuttal.

7

0

10

@hankyang94

Heng Yang

1 year

Going to #CVPR2023 ? Grab the "PURSE" poster at West Building Exhibit Halls ABC 069!

@hankyang94

Heng Yang

2 years

#CVPR2023 highlight paper w/ @drmapavone : We combine #ConformalPrediction , #SetMembershipEstimation , #SemidefiniteRelaxation to perform pose estimation with "provably correct" uncertainty quantification: a worst-case error bound from the groundtruth

3

9

55

0

1

9

@hankyang94

Heng Yang

5 years

Check out our #CVPR2020 paper on Certifiably Optimal 3D Shape Reconstruction from 2D Landmarks in a single image. Camera-ready version here:

Tweet media one

0

2

9

@hankyang94

Heng Yang

4 years

Very happy to be a coauthor of @jingnanshi 's nice work about ROBIN, which applies invariance and graph theory to prune outliers in robot perception (like a charm)! Looking forward to exploring more applications of ROBIN.

@lucacarlone1

Luca Carlone

4 years

do you want to boost the robustness of your RANSAC/robust estimator? Check this preprint showing how to solve problems with >90% outliers using max clique and invariance: we prune outliers in milliseconds! #mitsparklab #robustPerception #computerVision

2

5

34

0

3

9

@hankyang94

Heng Yang

1 year

We learned a lot from you, thanks for coming!!

@lin_haohong

Haohong Lin

1 year

Grateful for the enlightening discussion on causal RL with @hankyang94 and the amazing group of peers at Harvard SEAS! 🙌 Thanks for the wonderful accommodation and the lunch at HBS 🙈

Tweet media one

0

0

16

1

0

9

@hankyang94

Heng Yang

3 months

Flying to Oxford tomorrow for #L4DC to present the "sister paper" of CLOSURE, where we use SOS relaxations to find outer approximations of uncertainty sets!

0

0

8

@hankyang94

Heng Yang

2 years

How to apply: (1) Choose an area (e.g., EE, CS, AM) for your PhD application (e.g., ) (2) Submit the official application (e.g., ) (3) List me as a potential faculty to work with in the application Thanks and best of luck!

0

0

7

@hankyang94

Heng Yang

3 years

If you have polynomial optimizations in your applications and you care about certifiable global optimality. Let us know. Deeply grateful to collaborators from NUS who are world-renowned SDP experts!

1

0

8

@hankyang94

Heng Yang

4 years

ADAPT and GNC are both in GTSAM and Matlab now!

@lucacarlone1

Luca Carlone

4 years

our outlier-robust algorithms for SLAM and geometric perception are now available in GTSAM and MATLAB: pointers to code after the abstract here: . see also: #mitSparkLab #robustPerception

1

6

34

0

1

8

@hankyang94

Heng Yang

2 years

My cat Cola was born in NYC. So #dalle created a portrait for him! “A black and white British shorthair drinking Coca-Cola in New York City, digital art” Fun fact is if I change NYC to Boston it does not work. Should collect some Boston training data :)

Tweet media one

0

0

8

@hankyang94

Heng Yang

4 years

This is THE ONE paper to read if you want to learn robust estimation in robot perception.

@lucacarlone1

Luca Carlone

4 years

New SPARK pre-print shows how to simultaneously do robust estimation and learn the inlier noise statistics (among many other cool results) - check out our minimally-tuned algorithms: . #mitsparklab #robustEstimation #robotperception

1

6

34

0

1

8

@hankyang94

Heng Yang

4 years

Thanks to Di Wang, TEASER++ now runs in Windows!

Tweet card media

GitHub - DrGabor/WinTeaser: Point cloud registration algorithm Teaser++ in Win10 and Visual Studio...

Point cloud registration algorithm Teaser++ in Win10 and Visual Studio 2015 - DrGabor/WinTeaser

0

1

8

@hankyang94

Heng Yang

4 years

Feel that reviewers are so good at picking common weaknesses (novelty and experiments). Do they even read the paper carefully enough to understand the novelty and significance that authors want to say through the experiments? A good researcher should learn to appreciate, too.

@JustinMSolomon

Justin Solomon

@JustinMSolomon

4 years

That time of year where I wonder why we all stake our careers on a glorified random number generator whose output we regard as a respected mark of quality. \end{rant}

2

9

97

0

1

8

@hankyang94

Heng Yang

11 months

Exciting work!

@yuewang314

Yue Wang

11 months

Introducing EmerNeRF, our answer to the challenging dynamic NeRF in-the-wild problem. EmerNeRF is the best-ever project I've got involved in, led by our only @JiaweiYang118 (stay tuned for his even more impressive works), in collaboration with @NVIDIAAI colleagues @iamborisi

Tweet media one

Tweet media two

Tweet media three

Tweet media four

5

30

216

0

0

6

@hankyang94

Heng Yang

5 years

Many people have tried TEASER and I am glad to see TEASER works great for their applications! New demos and examples will make TEASER even easier to use 😃

@lucacarlone1

Luca Carlone

5 years

Fast and certifiably robust point cloud registration with TEASER++. New demos and examples available here:

0

11

52

0

0

7

@hankyang94

Heng Yang

4 years

🚀🚀

@lucacarlone1

Luca Carlone

4 years

Our paper on robust spatial perception is a finalist for the Best Paper Award in Robot Vision at ICRA 2020! The paper provides a general framework to extend newly developed global solvers for 3D vision to problems with outliers. #mitSparkLab

1

9

89

1

0

7

@hankyang94

Heng Yang

2 years

Excited to attend ICCOPT and present STRIDE for solving rank-one semidefinite relaxations of polynomial optimization problems, with applications in robot perception! Session: Recent Developments in Solving Structured Semidefinite Programs When: Wednesday July 27th 2:20pm

0

0

7

@hankyang94

Heng Yang

4 years

Check out cool #icra2021 papers from SPARK Lab!

@lucacarlone1

Luca Carlone

4 years

SPARK has 2 cool papers accepted at #ICRA2021 : - ROBIN: a general tool to remove outliers in perception () - Kimera-Multi: a distributed multi-robot system for dense metric-semantic SLAM () #mitsparklab #robotperception #ComputerVision

0

6

53

0

0

7

@hankyang94

Heng Yang

1 year

Is there an infinite-horizon continuous-time optimal control problem with control saturation for which we know the analytical optimal value function?

1

0

7

@hankyang94

Heng Yang

5 months

@antoine_leeman @Modern_Gangster For trajectory optimization problems that can be written as polynomial optimization problems (e.g., using Lie group variational integrators), one can apply a sparse moment-SOS relaxation that is empirically tight at the second order (as shown by a paper last RSS). We make this

0

0

6

@hankyang94

Heng Yang

3 years

Exciting!

@GeorgiaChal

Georgia Chalvatzaki

3 years

We are very excited to host #RSSPioneers21 @RoboticsSciSys Scroll into our Pioneeers' research statements👉 Get to know our rising stars and interact with them at the main #RSS2021 interactive poster session on Monday 👉

0

8

43

0

0

6

@hankyang94

Heng Yang

2 years

Check out new preprint on category-level outlier-robust object pose and shape estimation from 2D and 3D keypoints!

@lucacarlone1

Luca Carlone

2 years

In this preprint, @jingnanshi and @hankyang94 investigate category-level object pose and shape estimation from 2D and 3D keypoints and propose an elegant and general framework for graph-theoretic outlier rejection: #mitSparkLab

1

5

13

0

1

6

@hankyang94

Heng Yang

2 years

(i) A MULTILEVEL polynomial optimization formulation (ii) Reduction to single-level and min-max polynomial optimization via KKT conditions (iii) Single-stage and two-stage semidefinite relaxations with asymptotic global convergence w/ Shucheng Kang, @Yuxiao_Chen_ , @drmapavone

0

0

6

@hankyang94

Heng Yang

3 months

To be presented at the #RSS2024 Lifelong Robot Learning workshop:

Tweet card media

Lifelong Robot Learning

Abstract

sites.google.com

0

0

5

@hankyang94

Heng Yang

1 year

Very cool!

@drmapavone

Marco Pavone

1 year

Releasing TBSIM (), a comprehensive framework to train and evaluate data-driven agent models for AV simulation. I hope this tool will catalyze research on this critical topic. @NVIDIADRIVE @NVIDIAAI @Yuxiao_Chen_ @danfei_xu @iamborisi

0

7

41

0

0

4

@hankyang94

Heng Yang

4 years

This is jaw-dropping🤯

0

0

5

@hankyang94

Heng Yang

9 months

The punchline: With clever loss functions, we can distill the optimal value function into a simple neural network. The neural value function induces a controller that also globally swings up and stabilizes the pendulum! So proud of Haoyu! (n/n)

Tweet media one

0

1

5

@hankyang94

Heng Yang

3 months

@du_yilun @KempnerInst Congrats Yilun, and welcome!!

0

0

5