Andrei Bârsan (@andreib) header
Andrei Bârsan (@andreib) profile picture

Robotics researcher @waabi_ai | PhD candidate at the University of Toronto | Past: Uber ATG Toronto | Opinions are my own, etc.

Adamstown, Pitcairn Islands
Joined April 2009
Photo by Andrei Bârsan (@andreib)Photo by Andrei Bârsan (@andreib)Photo by Andrei Bârsan (@andreib)Photo by Andrei Bârsan (@andreib)Photo by Andrei Bârsan (@andreib)Photo by Andrei Bârsan (@andreib)Photo by Andrei Bârsan (@andreib)Photo by Andrei Bârsan (@andreib)Photo by Andrei Bârsan (@andreib)
My colleagues and I are presenting an 11-part tutorial on self-driving autonomy and simulation! Come check it out @CVPR on Tuesday! waabi.ai/cvpr-2024/
Headed to @CVPR? Join our full day tutorial titled, “All You Need to Know About Self-Driving,” on Tues, June 18 at 9am in room Summit 445. We’ll also present our paper, UnO: Unsupervised Occupancy Fields for Perception and Forecasting, on Thurs, June 20! waabi.ai/join-us-at-cvpr-202…
1
6
371
We are really excited about the release!! The dataset is live now with instructions and an example notebook. The sequences are specially selected to be very challenging! Please feel free to reach out to either Joyce or myself with any questions! 😃
📢📢📢 The AMV-Bench dataset is now released! This SLAM benchmark features 7 cameras (including a stereo pair) and 116 sequences of real-world driving with high-quality ground-truth, diverse environments, weather and motion paths. Check out bit.ly/amv-slam for more!
1
7
726
What makes LiDAR look realistic to a self-driving car? 🤖🚗Come check out our #ICCV2023 poster, "Towards Zero Domain Gap: A Study of Realistic LiDAR Simulation for Autonomy Testing" to find out! Thu 10:30am CET, Nord 011 PDF, Video, etc.: waabi.ai/lidar-dg/
2
6
2
31
3,782
This is a joint work with Siva Manivasagam, @wangjksjtu, @yangze0930, and @urtasun!
1
1
145
In this example, we see that baseline LiDAR sim can lead to flickering which is not present in the real detections. However, when we adapt the baseline by transferring the secondary returns from real data, the flickering disappears - highlighting the importance of this effect!
4
128
Excited to be part of @Waabi_ai's #CVPR2023 tutorial on #AutonomousVehicles! If you are interested in learning about how AVs work, from hardware to algorithms, come check us out Mon Jun 19 at 9am PT in Room West 302-305 cvpr2023.waabi.ai
7
486
Andrei Bârsan retweeted
Can we build 3D digital twins scalably from sensor data captured by a moving platform and use them for realistic and controllable simulation? Check our paper CADSim openreview.net/forum?id=Mp3Y…, presenting tmr at #CoRL2022 (Spotlight & Poster: 9:35-10:50 AM, OGG-FPAA & Room 040B-C)!
2
12
57
7,570
Very grateful to have had the opportunity to be a (small) part of Waabi since Day 1. And this is just the beginning. Exciting times ahead!
I am so proud of @Waabi_ai team and everything we have achieved only 6 months on from our launch. Waabi World is the next generation of simulation technology and will be the key to unlocking self-driving at scale. We’re so excited about what’s to come! waabi.ai/waabi-world/
1
Well, looks like @GitHubCopilot is aware of the most important aspects of software 🤔🤔
1
9
Also, took a bit of work prompting it, but it seems Copilot is also aware of Bee Movie... ...I'm not sure what I should do with this information
2
Our #CVPR2021 self-driving tutorial is live right now! Watch it live on zoom (link on cvpr2021.waabi.ai) or on YouTube! youtube.com/watch?v=-nr7-PQQ… Each session has its own Q&A. Feel free to ask questions either on YT or on Zoom!
4
23
We're doing a big #CVPR2021 tutorial on self-driving cars, from hw to maps, planning, V2V and more! Starts Jun 20, 10am EDT. Very excited & grateful to be part of it: I'll be covering parts of localization & hardware! More info: cvpr2021.waabi.ai/
1
11
49
Today at 4pm EDT we're presenting Asynchronous Multi-View SLAM at #ICRA2021 🤖🚗 Large-scale #SLAM for async multi-camera robots and a new 480km benchmark w/ 100+ sequences. Who: @ajyang99, Can Cui, @RaquelUrtasun, @ShenlongWang Web: https://nitter.cf/t.co/T5JPamnHoA 🧵⬇️ (1/5)
2
11
3
61
Contribution B: New large-scale outdoor SLAM benchmark: 7 HD cameras, 480km, 100+ sequences, high quality GT poses from fused GPS+LiDAR maps. We use it to show the importance of multiple cameras and modeling sensors as async. Dataset & code release timeline coming soon! (4/5)
1
5
The PDF, additional results, and videos are on the project website: https://nitter.cf/t.co/T5JPamnHoA ICRA live talk links have been sent to registered attendees (check out track 8). We’ll release the talk video after ICRA! (5/5)
5
Awesome work in streaming 3D perception for low-latency autonomy! 🤖
Want to reduce the latency of your self-driving autonomy system by 100ms? Check our work to learn how to perform perception without waiting for the LiDAR sweep to be built!
Check this out! How to solve inverse problems in an efficient and scalable manner while leveraging the observations to give feedback to the network.
Tired of hand-crafting energy functions for your inverse problems? Bored of deep nets predicting estimations that are not coherent with the observations? Deep feedback inverse problem solver to the rescue! It’s fast, robust, and generic! #ECCV2020 #Spotlight
4
21