Xuxin Cheng
@xuxin_cheng
Followers
2,736
Following
950
Media
18
Statuses
510
Robot Learning; Embodied AI; PhD @UCSanDiego MS @CarnegieMellon Prev @UCBerkeley
San Diego, CA
Joined November 2016
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
ميلان
• 1226913 Tweets
BRICS
• 283516 Tweets
Öcalan
• 269410 Tweets
Özgür Özel
• 78700 Tweets
Ümit Özdağ
• 70603 Tweets
NEVER BORED ON NINGNING DAY
• 57510 Tweets
#النصر_الاستقلال
• 53873 Tweets
Eminem
• 52773 Tweets
Blade
• 52702 Tweets
Valdivia
• 52516 Tweets
桜井政博
• 49100 Tweets
Siya
• 42690 Tweets
Celtics
• 39942 Tweets
Dortmund
• 36612 Tweets
Bicol
• 32627 Tweets
APO PİÇTİR PİÇ KALACAK
• 29415 Tweets
Türkiye Türk'tür
• 25957 Tweets
桜井さん
• 23837 Tweets
Knicks
• 19543 Tweets
Yoru
• 17372 Tweets
TXT YOU ARE LOVED
• 14430 Tweets
Yunus Akgün
• 13677 Tweets
#راكان_السهلي_في_شاعر_الرايه
• 11867 Tweets
Pulisic
• 10573 Tweets
Denji
• 10398 Tweets
Pinned Tweet
Introduce Open-𝐓𝐞𝐥𝐞𝐕𝐢𝐬𝐢𝐨𝐧🤖:
We need an intuitive and remote teleoperation interface to collect more robot data.
𝐓𝐞𝐥𝐞𝐕𝐢𝐬𝐢𝐨𝐧 lets you immersively operate a robot even if you are 3000 miles away, like in the movie 𝘈𝘷𝘢𝘵𝘢𝘳.
Open-sourced!
37
227
1K
Many folks are interested in the latency and speed of 𝐓𝐞𝐥𝐞𝐕𝐢𝐬𝐢𝐨𝐧.
We put the operator and the robot side-by-side so you can have a better perception of the latency and speed of 𝐓𝐞𝐥𝐞𝐕𝐢𝐬𝐢𝐨𝐧.
Check out more in the main thread 🧵.
Introduce Open-𝐓𝐞𝐥𝐞𝐕𝐢𝐬𝐢𝐨𝐧🤖:
We need an intuitive and remote teleoperation interface to collect more robot data.
𝐓𝐞𝐥𝐞𝐕𝐢𝐬𝐢𝐨𝐧 lets you immersively operate a robot even if you are 3000 miles away, like in the movie 𝘈𝘷𝘢𝘵𝘢𝘳.
Open-sourced!
37
227
1K
15
102
534

🤖Introducing 📺𝗢𝗽𝗲𝗻-𝗧𝗲𝗹𝗲𝗩𝗶𝘀𝗶𝗼𝗻: a web-based teleoperation software!

🌐Open source, cross-platform (VisionPro & Quest) with real-time stereo vision feedback.

🕹️Easy-to-use hand, wrist, head pose streaming.
Code:
14
91
378
14k usd humanoid robot is coming. 23-43dofs, dex hands, 35kg. Insane
@UnitreeRobotics
. H1 is ~100k, released one year ago.
21
69
371
Introduce Open-𝐓𝐞𝐥𝐞𝐯𝐢𝐬𝐢𝐨𝐧: Autonomous Skills
The high-quality data can be readily used for imitation learning. We train fully autonomous policies on a series of precise and long-horizon tasks, including:
- Insertion
- Sorting
- In-hand Passing
- Folding
1
49
258
3 papers accepted to CoRL2024!
All open-sourced.
TeleVision:
ACE:
VBC:
8
10
192
Try 𝐓𝐞𝐥𝐞𝐕𝐢𝐬𝐢𝐨𝐧 now without any setup:
It will display a 3D movie recorded during teleoperation.
If you open the link with a VR device it will be a 3D movie. You can also see your hand key points if you use VR.
Introduce Open-𝐓𝐞𝐥𝐞𝐕𝐢𝐬𝐢𝐨𝐧🤖:
We need an intuitive and remote teleoperation interface to collect more robot data.
𝐓𝐞𝐥𝐞𝐕𝐢𝐬𝐢𝐨𝐧 lets you immersively operate a robot even if you are 3000 miles away, like in the movie 𝘈𝘷𝘢𝘵𝘢𝘳.
Open-sourced!
37
227
1K
4
14
136
We are presenting 𝐄𝐱𝐩𝐫𝐞𝐬𝐬𝐢𝐯𝐞 𝐇𝐮𝐦𝐚𝐧𝐨𝐢𝐝 at
#RSS2024
on July 18th at 11:30am by
@JiYandong
!
The code is now 𝐨𝐩𝐞𝐧-𝐬𝐨𝐮𝐫𝐜𝐞𝐝!
👉
All of my 4 recent works have been open-sourced now. 👇
Let’s think about humanoid robots outside carrying the box. How about having the humanoid come out the door, interact with humans, and even dance?
Introducing Expressive Whole-Body Control for Humanoid Robots:
See how our robot performs rich, diverse,
93
209
1K
5
17
126
TeleVision plays a role in the latest exciting progress at
#NVIDIA
. Can't wait to see what's next at GEAR!
1
8
113
Didn't think this is possible but we made it! Glad to finish my master with this exciting project with amazing collaborators
@teenhaci
,
@anag004
and
@pathak2206
!
Even after 4yrs of locomotion research, we keep getting surprised by how far we can push the limits of legged robots! We report a major update 🚀🤖
Extreme Parkour: extremely long & high jumps, ramp, handstand, etc. all with a single neural net!
🧵(1/n)
26
231
1K
7
10
95
Robots have always been asked to work. We explore the other direction what robot can do. Expressive Humanoid takes motions from Mocap, generative model, video2motion model, and then show them in the real world with whole-body movements,💃enabling natural human-robot interactions.
Let’s think about humanoid robots outside carrying the box. How about having the humanoid come out the door, interact with humans, and even dance?
Introducing Expressive Whole-Body Control for Humanoid Robots:
See how our robot performs rich, diverse,
93
209
1K
4
16
88
Check out TeleVision that is behind this cool demo from unitree.
1
12
86
Humanoid whole body grasp and trajectory tracking for any objects. Can’t wait to see it working on real robots!
Introducing Omnigrasp: Grasping Diverse Objects with Simulated Humanoids.
With Omnigrasp, we show that we can control a humanoid equipped with dexterous hands to grasp diverse objects (>1200) and follow diverse trajectories, with one policy!
🌐:
📜:
3
71
313
2
12
85
Check out our low-cost 3D printable exoskeleton system that can teleoperate many robots!
Open-sourced!
Introducing ACE - A Cross-Platform Visual-Exoskeletons System!
Control all your robots with precision, all at once, with minimal cost, quick assembly, and easy wearability!
We’ve open-sourced hardware, software, and step-by-step assembly guides. Get started today!
👉🏻
4
64
318
0
9
75
Dr. Jim Fan mentioned it is "non-trivial to set up the software to have first-person video streamed in and precise control streamed out".
Try out our open-sourced teleoperation software 📺Open-TeleVision: (Under continuous improvement!)
Congrats to
@Tesla_Optimus
team on another stellar update! The video gives us a peek at their human data collection farm, which I believe is Optimus' biggest lead. What does it take to build such a pipeline? Optimus nailed all of the following:
1. Optimus hands are among the
131
421
3K
1
10
68
Check out our "Doggybot" series of works: Helpful Doggybot.
1 DoF gripper + whole-body movements enables helpful fetching and agile traversal of home environments!
Feel free to include "Doggybot" in your project to explore more what quadrupeds can do!
Introducing Helpful DoggyBot🐕, a legged mobile manipulation system:
- A quadruped with a mouth
- Agile whole-body skills like climbing and tilting
- Open-world object fetching using VLMs
- No real-world training data required!
5
44
253
1
12
66
Extreme Parkour was accepted at
@ieee_ras_icra
2024. Won’t be possible without the joint efforts with
@teenhaci
@anag004
@pathak2206
!
Didn't think this is possible but we made it! Glad to finish my master with this exciting project with amazing collaborators
@teenhaci
,
@anag004
and
@pathak2206
!
7
10
95
2
4
63
Knowing why something fails is extremely important for research. Really rare to see such papers of lessons learned from failures.
When I started my first project on in-hand manipulation, I thought it would be super cool but also quite challenging to make my robot hands spin pens. After almost 2.5 years of effort in this line of research, we have finally succeeded in making our robot hand "spin pens."
22
80
526
0
7
61
Not possible without the joint efforts of
@Jialong_LI_UIM
@AaronYANG2000
@EpisodeYang
@xiaolonw
Try now even if you don’t have a VR device!
More videos, code, hardware, and dataset at:
2
2
60
The tracking performance is truly amazing! Congrats!
For stability, we track gripper actions in world frame instead of body frame, like most prior works. So, when our robot is pushed, its arm will compensate the perturbation.
To support real world deployment, we mount an iPhone on the dog’s 🍑, running a custom iOS ARKit app.
3
6
51
0
7
48
A summary of our findings regarding data collection for robotics through three projects we have been doing and open-sourced.
We hope the open-sourced software and hardware will benefit the community and converge to a better system.
3
4
46
Teleoperating robots will be as common as driving your car (also robots). Congratulations to the team on the amazing whole-body results towards this goal!
Introduce HumanPlus - Shadowing part
Humanoids are born for using human data. We build a real-time shadowing system using a single RGB camera and a whole-body policy for cloning human motion. Examples:
- boxing🥊
- playing the piano🎹/ping pong
- tossing
- typing
Open-sourced!
17
165
770
1
7
45
Checkout our live demos at
#CoRL2023
!
Live demos of our parkour robot in Atlanta during
@CoRL2023
. 🤖🚀
Check out this uncut 2mins clip of our robot nonstop climbing, leaping across gaps, and jumping down from boxes! More videos:
A fun story below how we overcame hardware issues onsite👇
2
12
155
1
0
43
Check out extreme-parkour presented by Kexin 16:30-18:00 on May 15 in AX F205
@icra2024
.
I will give an oral presentation about Extreme Parkour with Legged Robots at
#ICRA2024
. It will happen at 16:30-18:00 on May 15 in AX F205. Feel free to join in if you are interested in RL for Locomotion!
Link:
Co-authors:
@xuxin_cheng
@anag004
@pathak2206
4
8
76
1
6
42
Our latest work on extending legs of quadruped beyond locomotion towards manipulation dexterity!
While we have made progress towards replicating the agility of animal mobility in robots, legs aren't just for walking, they are extended arms!
Our
#ICRA
2023 paper enables legs to act as manipulators for agile tasks: climbing walls, pressing button etc.
3
72
357
0
5
40
Real-time stereo video streaming provides spatial/depth understanding, so the operator is confident about the objects’ locations. This enables fine manipulation with challenging objects such as transparent boxes.
2
4
37
Thanks for
@NVIDIAGTC
for featuring our live demo at GTC! Wouldn’t be possible without
@UnitreeRobotics
‘s technical support.
Website:
Dancing robots at
#GTC24
🕺
You can feel the excitement leading up to NVIDIA CEO Jensen Huang's keynote on Monday just outside the SAP center.
@UnitreeRobotics
6
27
146
0
2
38
Our latest work on Deep Whole-Body Control that will appear
@corl_conf
2022. Detailed explanation thread is coming soon. Stay tuned!
Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion
abs:
project page:
3
58
298
1
8
37
LLM proven to be able to engineer reward & sim2real params that make things work in the real world.
Introducing DrEureka🎓, our latest effort pushing the frontier of robot learning using LLMs!
DrEureka uses LLMs to automatically design reward functions and tune physics parameters to enable sim-to-real robot learning. DrEureka can propose effective sim-to-real configurations
25
118
601
0
3
37
Now you can teleop an RL comtrolled quadruped to do BC. Very cool!
Quadruped robots already have four manipulators (aka legs), do we really need extra arms for them? 🤔
Dive into our latest work: quadruped robots handle complex loco-manipulation tasks autonomously with just legs! 🐾
1
21
91
1
3
34
Further testing our walking robustness on all kinds of terrains.
12
19
190
1
2
30
Human motions will provide immense amounts of data for robot control!
🤖 Introducing H2O (Human2HumanOid):
- 🧠 An RL-based human-to-humanoid real-time whole-body teleoperation framework
- 💃 Scalable retargeting and training using large human motion dataset
- 🎥 With just an RGB camera, everyone can teleoperate a full-sized humanoid to perform
23
98
486
0
0
29
Very natural motions learned from animal videos!
Introducing my recent collaboration work, "Spatio-Temporal Motion Retargeting for Quadruped Robots" co-authored with Taerim Yoon, Seungmin Kim, Minsung Ahn, Stelian Coros, and Sungjoon Choi.
2
6
57
1
2
28
Checkout our new work on autonomous whole-body picking for a large quadruped robot! 🦾
Sim-to-real again shows generalization, scalability on a range of tasks that can be well defined.
I have been cleaning my daughter's mess for more than two years now. Last weekend our robot came to home to do the job for me. 🤖
Our new work on visual whole-body control learns a policy to coordinate the robot legs and arms for mobile manipulation. See
23
115
653
0
2
27
The system is easily accessible from any device with a web browser (Vision Pro, Quest, even mac, iPad, iPhone…).
2
1
22
An active neck plus IK and retargeting enables intuitive perception and actuation for the operator. The operator just needs to look at the points of interest intuitively and the robot will follow the same head movements.
1
2
23
Really cool work on loco-manipulation!
LocoMan
= Quadrupedal Robot + 2 * Loco-Manipulator
Powered by dual lightweight 3-DoF Loco-Manipulators and the Whole-Body Controller, LocoMan achieves various challenging tasks, such as manipulation in narrow spaces and bimanual-manipulation.
👇👇👇
6
48
220
1
5
21
On second thought, it might be even harder for a humanoid to parkour on these obstacles compared to quadrupeds. Congrats and amazing results!
Introducing 🤖🏃Humanoid Parkour Learning
Using vision and proprioception, our humanoid can jump over hurdles, and platforms, leap over gaps, walk up/down stairs, and much more.
🖥️Check our website at
📺Stay tuned for more videos.
14
92
458
0
1
21
@tonyzzhao
Maybe it is not appropriate to claim "fully open source" because only training code is open-sourced but both hardware code and how pose estimation is incorporated are not open-sourced. Please correct me if I have any misunderstanding.
1
0
19
Mobile manipulation now goes to the wild with custom built cheap hardware.
Imitation learning +Online RL ➡️ auto adaptation to novel in-the-wild articulated objects.
Introducing Open-World Mobile Manipulation 🦾🌍
– A full-stack approach for operating articulated objects in open-ended unstructured environments:
Unlocking doors with lever handles/ round knobs/ spring-loaded hinges 🔓🚪
Opening cabinets, drawers, and refrigerators 🗄️
👇
30
104
774
0
1
18
Feature injected generalizable NeRF now helps real robots understand the environment and execute tasks in the wild!
We have seen a lot of legged robots doing navigation in the wild. But how about mobile manipulation in the wild?
I have been pushing the direction of learning a unified, efficient, and dynamic 3D representation of scenes (for navigation) and objects (for manipulation) for the
5
49
237
0
2
17
Congrats!
Check out more about open-sourced Extreme-Parkour project:
📣 Excited to share
@CRV
's investment in the
@SkildAI
Series A round!
When I was building robots ~10 years ago for Rehabilitation Institute of Chicago, one of the biggest challenges was having robotics perform extreme parkour. Two researchers
@pathak2206
and
@gupta_abhinav_
2
4
70
0
0
17
Open source robotics is the way!
Meet LeRobot, my first library at
@huggingface
robotics 🤗
The next step of AI development is its application to our physical world. Thus, we are building a community-driven effort around AI for robotics, and it's open to everyone!
Take a look at the code:
35
216
837
0
0
17
Xarm can do skincare for you! Checkout Bunny-VisionPro: open sourced vision teleoperation with motion retargeting code.
Tesla Optimus can arrange batteries in their factories, ours can do skincare (on
@QinYuzhe
)!
We opensource Bunny-VisionPro, a teleoperation system for bimanual hand manipulation. The users can control the robot hands in real time using VisionPro, flexible like a bunny. 🐇
10
62
335
0
1
17
Perhaps the most Impressive bipedal locomotion result I have seen! from
@ZhongyuLi4
.
Interested in making your bipedal robots to be athletes? We summarized our RL work to create robust & adaptive controllers for general bipedal skills. 400m-dash, running over terrains/against perturbations, targeted jumping, compliant walking, not a problem for bipeds now.🧵👇
15
89
451
0
0
15
Really impressive! Parallel grippers can already achieve so many complex tasks. Looking forward to the moment when the one take video extends to hours and the robots being the only employees in a robot repair workshop!
Introducing 𝐀𝐋𝐎𝐇𝐀 𝐔𝐧𝐥𝐞𝐚𝐬𝐡𝐞𝐝 🌋 - Pushing the boundaries of dexterity with low-cost robots and AI.
@GoogleDeepMind
Finally got to share some videos after a few months. Robots are fully autonomous filmed in one continuous shot. Enjoy!
55
342
2K
1
0
15
Teleoperating a robot to use a joystick to play a game is insane!
To address the first challenge, we develop HATO ("dove" 🕊️ in Japanese), a low-cost Hands-Arms TeleOperation system using Meta Quest 2.
Our system demonstrates precise motion control capabilities and human-like dexterity -- we even controlled our robot to play Hollow Knight!
1
6
29
0
1
14
3D visual language feature helps semantic understanding of the environments!
Introducing DNAct: Diffusion Guided Multi-Task 3D Policy Learning.
We combine neural rendering pre-training and diffusion models to learn a generalizable policy with a strong 3D semantic scene understanding.
2
20
89
0
4
14
Very cool and fast progress! Congratulations!
Introduce OmniH2O, a learning-based system for whole-body humanoid teleop and autonomy:
🦾Robust loco-mani policy
🦸Universal teleop interface: VR, verbal, RGB
🧠Autonomy via
@chatgpt4o
or imitation
🔗Release the first whole-body humanoid dataset
24
74
417
1
0
13
Nice benchmark on humanoid locomotion and manipulation. Model-based RL Like TD-MPC2 showed very impressive performance! We might want hierachical policies for long horizon tasks.
Humanoids 🤖 will do anything humans can do. But are state-of-the-art algorithms up to the challenge?
Introducing HumanoidBench, the first-of-its-kind simulated humanoid benchmark with 27 distinct whole-body tasks requiring intricate long-horizon planning and coordination.
🧵👇
8
92
335
0
1
13
Glad to see TeleVision is used by 1x! It is really a magical experience to transmit your mind to a robot embodiment
. Maybe in the future everyone will get used to it.
A week ago I embodied myself in a humanoid robot from inside a VR headset.
It was very weird to look down and see I had robot hands.
Here is how.
12
26
108
0
1
13
@StamatisTWIY
We built upon Unitree H1 robot and Fourier GR-1 robot. The hands are from Inspire robots. The active cam part of H1 is customized and open-sourced. We use non-modified hardware for GR-1.
1
2
12
VR’s potential is changing how we interact with virtual and real. Very cool project!
Thrilled to share our
#SIGGRAPH2024
work on physics-based character animation for ping pong!🏓We show not only agent-agent matches but also human-agent interactions via VR, allowing humans to challenge our trained agents!🎮
🌐:
📜:
5
20
112
2
1
12
@EpisodeYang
is truly a great collaborator. Our system is built upon Vuer developed by Ge. Vuer’s capability is more than this and can be useful for all kinds of robotics visualizations.
@TairanHe99
@EpisodeYang
is an incredible full stack engineer in building this kind of complex software stack. I know the system is good the moment I saw his name on it!
1
1
9
1
2
11
Excited to share our recent work on Deep Whole-Body Control. This work will appear in
#CoRL
'22 (Oral). And don’t miss the live demo sessions at
#CoRL
'22 in New Zealand!🤖
An arm can increase the utility of legged robots. But due to high dimensionality, most prior methods decouple learning for legs & arm.
In
#CoRL
'22 (Oral), we present an end-to-end approach for *whole-body control* to get dynamic behaviors on the robot.
7
47
299
0
0
11
Glad to see more and more open sourced robotics project! 🎉
Exciting news! We've just released the source code for our WASABI project, a CoRL 2022 best paper finalist, aimed at mastering agile skills through adversarial imitation from rough, partial, handheld demonstrations! Check it out: . 🚀
1
8
79
0
0
10
Open-TeleVision:
Visual-Whole-Body:
Expressive-Humanoid:
Extreme-Parkour:
1
3
10
Thanks for covering our work! Intel RealSense cameras have empowered our robot with unprecedented agile skills!
This
#ICRA2023
paper is being presented this week - featuring
#IntelRealSense
technology. Very impressive!!
0
5
14
1
0
10
So much fun just to watch robots play! I see a lot of potentials what robots can do besides working.
Soccer players have to master a range of dynamic skills, from turning and kicking to chasing a ball. How could robots do the same? ⚽
We trained our AI agents to demonstrate a range of agile behaviors using reinforcement learning.
Here’s how. 🧵
132
521
2K
0
2
10
A great post about the concept of machine unlearning while current models are learning more and more.
The idea of "machine unlearning" is getting attention lately. Been thinking a lot about it recently and decided to write a long post: 📰
Unlearning is no longer just about privacy and right-to-be-forgotten since foundation models. I hope to give a gentle
22
162
749
0
1
8
Live talks happening now across 3 workshops
@corl_conf
!
Deployable at Station;
Generalist at Sequoia 1;
Roboletics at Muse2!
0
0
7
@tonyzzhao
Thanks Tony! The academia is built upon open-sourced projects and shared knowledge to advance. We improved upon ACT, which is a really good codebase to use. Special thanks for open-sourcing it!
1
0
7
World models with limited robot data? Check out
@mendonca_rl
on shared world models between humans and robots!
World models are promising for enabling general-purpose robots. But how do we train them since robot data is limited?
Our solution: Shared world models on human videos and robots using affordances as the joint action space. Pre-train on human video, then fine-tune to robot tasks!
4
30
129
0
0
6
0
3
5
Cool work by
@anag004
@ashishkr9311
. Pushing locomotion to next level with visual feedback.
After 3yrs of locomotion research, we report a major update in our
#CoRL2022
(Oral) paper: vision-based locomotion.
Our small, safe, low-cost robot can walk almost any terrain: high stairs, stepping stones, gaps, rocks.
Stair for this robot is like climbing walls for humans.
34
159
895
0
1
5
This is truly incredible.
Unitree H1 The World's First Full-size Motor Drive Humanoid Robot Flips on Ground.
Unitree H1 Deep Reinforcement Learning In-place Flipping !
#Unitree
#UnitreeRobotics
#AI
#Robotics
#Humanoidrobots
#Worldrecord
#Flips
#EmbodiedAI
#ArtificialIntelligence
#Technology
#Innovation
69
414
2K
0
0
5
Not possible without the joint efforts of
@Jialong_LI_UIM
@AaronYANG2000
@EpisodeYang
@xiaolonw
Try now even if you don’t have a VR device! More videos, code, hardware, and dataset at:
0
1
5
@Haoyu_Xiong_
I think VR devices can be the core of the system. Depending on different tasks, accessories like haptic gloves, joint copy arms could be used.
0
0
4
Remote work can be extended to physical ones!
Hear me out:
1. Put the robots into the office, 1 robot per 1 engineer
2. Buy each robots a laptop
3. Connect and control from your home
4. Remote work solved!
0
1
16
1
0
4
We use a powerful DinoV2 visual backbone and a transformer to process multimodal information.
1
0
4
Agreed. If you notice in our demo, the 2 abduction motors for thumbs have both broken, but we can still do this task.
Indeed, we find that hands, even when used with limited DoFs, can perform a large set of tasks & outperform grippers because of the additional stability! This also allows for smoother and more intuitive teleop (e.g. no retargeting issue), leading to much faster data collection :D
0
0
6
2
0
3
The service is hosted on a small EC2 instance on AWS. The resolution is set low for preview in the beta stage.
0
0
3
Also inspired by Atlas dancing to the music. Atlas' motion is always elegant, expressive and ahead of time. We take the step to make motion imitation for real robots more general and affordable.
1
0
3
@TairanHe99
@EpisodeYang
Glad to see you made it work! For stereo streaming you can adjust the quality parameter without sacrificing resolution. A high bandwidth router will also significantly affect delay because of tcp. If you want only mono video stream, you can achieve low delay with high quality.
0
0
3
Thanks for featuring our work!
Researchers at UCSD and MIT introduced Open-TeleVision
It's an open-source tele-op system that allows users to control robots from thousands of miles away
It's also accessible from any device with a web browser, including VR
1
24
241
0
0
3
@Stone_Tao
Thanks Stone! OpenTeleVision is general to any video input and can be used for either sim or real. Looking forward to the next step of Maniskill3!
0
0
2
@Stone_Tao
Yes, as long as you can extract frames from your live video, it does not matter if it is sim or real.
0
0
2
@YunzhuLiYZ
@UofIllinois
@uofigrainger
@IllinoisCS
@StanfordSVL
@jiajunwu_cs
@drfeifei
Congratulations! 🎉
1
0
2
1
0
2
@ashishkr9311
@UCBerkeley
@Tesla
@Teslasbot
Congratulations Ashish! It was very pleasant working with you.
0
0
2
great work！
0
0
2
@ShivinDass
From my personal perspective, there is some jittering due to network bandwidth but totally ok to me. This can be further improved in future versions, by adding vignetting effect for example.
0
0
2