Drago Anguelov's guest appearances

Drago Anguelov

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

Gradient Dissent: Exploring Machine Learning, AI, Deep Learning, Computer Vision

The Gradient: Perspectives on AI

Sean Taylor

Xavier Amatriain

Emily M. Bender

Josh Bloom

Ion Stoica

Bharath Ramsundar

Kathryn Hume

Pieter Abbeel

Jeremy Howard

Adrien Gaidon

Hamel Husain

Josh Tobin

Suzana Ilić

Angela Bassa

Daphne Koller

OwlTail

In episode 69 of The Gradient Podcast, Daniel Bashir speaks to Drago Anguelov.Drago is currently a Distinguished Scientist and Head of Research at Waymo, where he joined in 2018. Earlier, he spent eight years at Google working on 3D vision and pose estimation for StreetView, then leading a research team that developed computer vision systems for annotating Google Photos. He has been involved in developing popular neural network methods such as the Inception architecture and the SSD detector. Before joining Waymo, he also led the 3D perception team at Zoox.Have suggestions for future podcast guests (or other feedback)? Let us know here or reach us at editor@thegradient.pubSubscribe to The Gradient Podcast:  Apple Podcasts  | Spotify | Pocket Casts | RSSFollow The Gradient on TwitterOutline:* (00:00) Intro* (02:04) Drago’s background in AI and self-driving, work with Daphne Koller + Sebastian Thrun, computer vision / pose estimation* (14:20) One- and two-stage object detectors* (15:15) Early experiences and thoughts on self-driving and its prospects* (21:00) An introduction to the “self-driving stack”: mapping &amp; localization, perception, behavior modeling &amp; planning, simulation* (29:25) From Stuart Russell’s comments on early Waymo’s “old-fashioned” approach* (37:34) Scaling 3D Detection: challenges and architectural innovations* (43:20) Behavior modeling: making decisions and modeling interactions in multi-agent environments* (52:42) Distributional RL (+ imitation learning) in self-driving?* (54:10) The Waymo Open Dataset* (1:01:48) Looking forward in self-driving* (1:04:36) OutroLinks:* Drago’s LinkedIn and Twitter* Research* SSD: Single-Shot Multibox Detector* SCAPE: Shape completion and animation of people* Behavior Models for Autonomous Driving* Wayformer* Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation* Imitation Is Not Enough* Scaling 3D Detection to the Long Tail Get full access to The Gradient at thegradientpub.substack.com/subscribe

In episode 69 of The Gradient Podcast, <a href="https://twitter.com/spaniel_bashir" rel="nofollow" target="_blank">Daniel Bashir</a> speaks to <a href="https://twitter.com/anguelovdrago" rel="nofollow" target="_blank">Drago Anguelov</a>.Drago is currently a Distinguished Scientist and Head of Research at Waymo, where he joined in 2018. Earlier, he spent eight years at Google working on 3D vision and pose estimation for StreetView, then leading a research team that developed computer vision systems for annotating Google Photos. He has been involved in developing popular neural network methods such as the Inception architecture and the SSD detector. Before joining Waymo, he also led the 3D perception team at Zoox.Have suggestions for future podcast guests (or other feedback)? Let us know here or reach us at editor@thegradient.pubSubscribe to The Gradient Podcast:  <a href="https://podcasts.apple.com/us/podcast/the-gradient-podcast/id1569777340" rel="nofollow" target="_blank">Apple Podcasts</a>  | <a href="https://open.spotify.com/show/6onNcSqsP6hEEqmZ6TU2g8" rel="nofollow" target="_blank">Spotify</a> | <a href="https://pca.st/itunes/1569777340" rel="nofollow" target="_blank">Pocket Casts</a> | <a href="https://api.substack.com/feed/podcast/265424/s/1354/private/3bbc085c-7aa9-4037-8784-1575653a0438.rss" rel="nofollow" target="_blank">RSS</a>Follow The Gradient on <a href="https://twitter.com/gradientpub" rel="nofollow" target="_blank">Twitter</a>Outline:* (00:00) Intro* (02:04) Drago’s background in AI and self-driving, work with Daphne Koller + Sebastian Thrun, computer vision / pose estimation* (14:20) One- and two-stage object detectors* (15:15) Early experiences and thoughts on self-driving and its prospects* (21:00) An introduction to the “self-driving stack”: mapping &amp; localization, perception, behavior modeling &amp; planning, simulation* (29:25) From Stuart Russell’s comments on early Waymo’s “old-fashioned” approach* (37:34) Scaling 3D Detection: challenges and architectural innovations* (43:20) Behavior modeling: making decisions and modeling interactions in multi-agent environments* (52:42) Distributional RL (+ imitation learning) in self-driving?* (54:10) The Waymo Open Dataset* (1:01:48) Looking forward in self-driving* (1:04:36) OutroLinks:* Drago’s <a href="https://www.linkedin.com/in/dragomiranguelov" rel="nofollow" target="_blank">LinkedIn</a> and <a href="https://twitter.com/anguelovdrago?lang=en" rel="nofollow" target="_blank">Twitter</a>* Research* <a href="https://arxiv.org/abs/1512.02325" rel="nofollow" target="_blank">SSD: Single-Shot Multibox Detector</a>* <a href="http://graphics.stanford.edu/courses/cs468-05-fall/Papers/p408-anguelov.pdf" rel="nofollow" target="_blank">SCAPE: Shape completion and animation of people</a>* <a href="https://www.youtube.com/watch?v=RpiN3LyMLB8" rel="nofollow" target="_blank">Behavior Models for Autonomous Driving</a>* <a href="https://waymo.com/research/wayformer-motion-forecasting-via-simple-and-efficient-attention-networks/" rel="nofollow" target="_blank">Wayformer</a>* <a href="https://arxiv.org/abs/2205.03195" rel="nofollow" target="_blank">Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation</a>* <a href="https://ml4ad.github.io/files/papers2022/Imitation%20Is%20Not%20Enough:%20Robustifying%20Imitation%20with%20Reinforcement%20Learning%20for%20Challenging%20Driving%20Scenarios.pdf" rel="nofollow" target="_blank">Imitation Is Not Enough</a>* <a href="https://www.youtube.com/watch?v=b84FbSZFJeQ" rel="nofollow" target="_blank">Scaling 3D Detection to the Long Tail</a> Get full access to The Gradient at <a href="https://thegradientpub.substack.com/subscribe?utm_medium=podcast&amp;utm_campaign=CTA_4" rel="nofollow" target="_blank">thegradientpub.substack.com/subscribe</a>

Drago Anguelov: Waymo and Autonomous Vehicles

Waymo

Drago Anguelov is a Distinguished Scientist and Head of Research at Waymo, an autonomous driving technology company and subsidiary of Alphabet Inc.We begin by discussing Drago's work on the original Inception architecture, winner of the 2014 ImageNet challenge and introduction of the inception module. Then, we explore milestones and current trends in autonomous driving, from Waymo's release of the Open Dataset to the trade-offs between modular and end-to-end systems.Drago also shares his thoughts on finding rare examples, and the challenges of creating scalable and robust systems.Show notes (transcript and links): http://wandb.me/gd-drago-anguelov---⏳ Timestamps: 0:00 Intro0:45 The story behind the Inception architecture13:51 Trends and milestones in autonomous vehicles23:52 The challenges of scalability and simulation30:19 Why LiDar and mapping are useful35:31 Waymo Via and autonomous trucking37:31 Robustness and unsupervised domain adaptation40:44 Why Waymo released the Waymo Open Dataset49:02 The domain gap between simulation and the real world56:40 Finding rare examples1:04:34 The challenges of production requirements1:08:36 Outro---Connect with Drago &amp; Waymo📍 Drago on LinkedIn: https://www.linkedin.com/in/dragomiranguelov/📍 Waymo on Twitter: https://twitter.com/waymo/📍 Careers at Waymo: https://waymo.com/careers/---Links:📍 Inception v1: https://arxiv.org/abs/1409.4842📍 "SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation", Qiangeng Xu et al. (2021), https://arxiv.org/abs/2108.06709📍 "GradTail: Learning Long-Tailed Data Using Gradient-based Sample Weighting", Zhao Chen et al. (2022), https://arxiv.org/abs/2201.05938---💬 Host: Lukas Biewald📹 Producers: Cayla Sharp, Angelica Pan, Lavanya Shukla---Subscribe and listen to our podcast today!👉 Apple Podcasts: http://wandb.me/apple-podcasts​​👉 Google Podcasts: http://wandb.me/google-podcasts​👉 Spotify: http://wandb.me/spotify​

Drago Anguelov is a Distinguished Scientist and Head of Research at Waymo, an autonomous driving technology company and subsidiary of Alphabet Inc.We begin by discussing Drago's work on the original Inception architecture, winner of the 2014 ImageNet challenge and introduction of the inception module. Then, we explore milestones and current trends in autonomous driving, from Waymo's release of the Open Dataset to the trade-offs between modular and end-to-end systems.Drago also shares his thoughts on finding rare examples, and the challenges of creating scalable and robust systems.Show notes (transcript and links): <a href="http://wandb.me/gd-drago-anguelov" rel="nofollow" target="_blank">http://wandb.me/gd-drago-anguelov</a>---⏳ Timestamps: 0:00 Intro0:45 The story behind the Inception architecture13:51 Trends and milestones in autonomous vehicles23:52 The challenges of scalability and simulation30:19 Why LiDar and mapping are useful35:31 Waymo Via and autonomous trucking37:31 Robustness and unsupervised domain adaptation40:44 Why Waymo released the Waymo Open Dataset49:02 The domain gap between simulation and the real world56:40 Finding rare examples1:04:34 The challenges of production requirements1:08:36 Outro---Connect with Drago &amp; Waymo📍 Drago on LinkedIn: <a href="https://www.linkedin.com/in/dragomiranguelov/" rel="nofollow" target="_blank">https://www.linkedin.com/in/dragomiranguelov/</a>📍 Waymo on Twitter: <a href="https://twitter.com/waymo/" rel="nofollow" target="_blank">https://twitter.com/waymo/</a>📍 Careers at Waymo: <a href="https://waymo.com/careers/" rel="nofollow" target="_blank">https://waymo.com/careers/</a>---Links:📍 Inception v1: <a href="https://arxiv.org/abs/1409.4842" rel="nofollow" target="_blank">https://arxiv.org/abs/1409.4842</a>📍 "SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation", Qiangeng Xu et al. (2021), <a href="https://arxiv.org/abs/2108.06709" rel="nofollow" target="_blank">https://arxiv.org/abs/2108.06709</a>📍 "GradTail: Learning Long-Tailed Data Using Gradient-based Sample Weighting", Zhao Chen et al. (2022), <a href="https://arxiv.org/abs/2201.05938" rel="nofollow" target="_blank">https://arxiv.org/abs/2201.05938</a>---💬 Host: Lukas Biewald📹 Producers: Cayla Sharp, Angelica Pan, Lavanya Shukla---Subscribe and listen to our podcast today!👉 Apple Podcasts: <a href="http://wandb.me/apple-podcasts​​" rel="nofollow" target="_blank">http://wandb.me/apple-podcasts​​</a>👉 Google Podcasts: <a href="http://wandb.me/google-podcasts​" rel="nofollow" target="_blank">http://wandb.me/google-podcasts​</a>👉 Spotify: <a href="http://wandb.me/spotify​" rel="nofollow" target="_blank">http://wandb.me/spotify​</a>

Drago Anguelov — Robustness, Safety, and Scalability at Waymo

Today we’re joined by Drago Anguelov, Distinguished Scientist and Head of Research at Waymo.  In our conversation, we explore the state of the autonomous vehicles space broadly and at Waymo, including how AV has improved in the last few years, their focus on level 4 driving, and Drago’s thoughts on the direction of the industry going forward. Drago breaks down their core ML use cases, Perception, Prediction, Planning, and Simulation, and how their work has lead to a fully autonomous vehicle being deployed in Phoenix.  We also discuss the socioeconomic and environmental impact of self-driving cars, a few research papers submitted to NeurIPS 2020, and if the sophistication of AV systems will lend themselves to the development of tomorrow’s enterprise machine learning systems. The complete show notes for this episode can be found at twimlai.com/go/454. 

Today we’re joined by Drago Anguelov, Distinguished Scientist and Head of Research at Waymo.  In our conversation, we explore the state of the autonomous vehicles space broadly and at Waymo, including how AV has improved in the last few years, their focus on level 4 driving, and Drago’s thoughts on the direction of the industry going forward. Drago breaks down their core ML use cases, Perception, Prediction, Planning, and Simulation, and how their work has lead to a fully autonomous vehicle being deployed in Phoenix.  We also discuss the socioeconomic and environmental impact of self-driving cars, a few research papers submitted to NeurIPS 2020, and if the sophistication of AV systems will lend themselves to the development of tomorrow’s enterprise machine learning systems. The complete show notes for this episode can be found at <a href="https://twimlai.com/go/454" rel="nofollow" target="_blank">twimlai.com/go/454</a>.

System Design for Autonomous Vehicles with Drago Anguelov - #454