
48 segments available
Oliver Cameron is the Co-Founder and CEO of Voyage. Before that he was the lead of the Udacity Self-Driving Car program that made ideas in autonomous vehicle research and development accessible to the world. For more lecture videos on deep learning, reinforcement learning (RL), artificial intelligence (AI & AGI), and podcast conversations, visit our website or follow TensorFlow code tutorials on our GitHub repo. INFO: Website: https://deeplearning.mit.edu GitHub: https://github.com/lexfridman/mit-deep-learning Playlist: http://bit.ly/2S1MVdy OUTLINE: 0:00 - Lex introducing Oliver 0:39 - Oliver background 4:40 - Udacity self-driving car engineer nanodegree program 14:10 - Autonomous trip from Mountain View to San Francisco 23:11 - Open source challenges 26:48 - Birth of Voyage 31:58 - Retirement communities 38:35 - Sensor and technology stack 40:45 - Example challenge for perception (foliage) 41:58 - Survey of recent perception research 45:51 - Lessons learned 48:45 - Q&A CONNECT: - If you enjoyed this video, please subscribe to this channel. - Twitter: https://twitter.com/lexfridman - LinkedIn: https://www.linkedin.com/in/lexfridman - Facebook: https://www.facebook.com/lexfridman - Instagram: https://www.instagram.com/lexfridman
Oliver Cameron, CEO of Voyage, introduces himself and shares his journey from leading the Udacity Self-Driving Car program to founding Voyage. He emphasizes the unconventional path of starting a self-driving car startup and the importance of learning by doing.
"all right welcome back to 6 s0 9 for deep learning for self-driving cars today we have Oliver Cameron is the co-founder and the CEO of voyage before that he was the lead of the Udacity self-driving ca..."
Oliver discusses the unconventional journey of starting Voyage, highlighting the zigzag path of entrepreneurship. He reflects on his learning style and how building software fueled his passion for technology, leading him to create impactful projects.
"thank you all for having me here today super excited to speak all about voyage but in reality the the kind of thing I want to share today is kind of like this title says how to start a self-driving ca..."
Oliver shares his pivotal moment of discovering MOOCs (Massive Open Online Courses) and how they transformed his understanding of artificial intelligence and robotics. He explains how this learning format inspired him to join Udacity and contribute to the self-driving car curriculum.
"learning in a classroom for me I found learning by doing by building has always been the thing that's that's worked best for me so going all the way back to when I was a teenager software just in gene..."
Oliver elaborates on his role at Udacity, where he led the development of the self-driving car curriculum. He discusses the importance of partnering with industry experts to create a curriculum that addresses real-world challenges in autonomous vehicle technology.
"format really just appealed to me being able to sit in my in front of my laptop learn at my own pace build build build was something that really resonated with me and I took this class in 2013 artific..."
Oliver explains Udacity's focus on teaching niche topics that align with emerging industry needs. He emphasizes the importance of preparing students for the rapidly evolving field of self-driving cars and the necessity of a broad skill set.
"talk about Udacity you raise your hand if you've heard of Udacity very curious there you go that's most of the room Udacity like I said was founded by Sebastian Thrun he took this class online and all..."
Oliver discusses the talent gap in the self-driving car industry and how Udacity aimed to accelerate the deployment of autonomous vehicles by training skilled engineers. He reflects on the skepticism faced when launching the self-driving car curriculum.
"the first one we did of this and we've done some after including flying cars a much more in-depth curriculum on artificial intelligence with self-driving cars so this is a quick video that introduces ..."
Oliver shares success stories of Udacity graduates who have gone on to work on groundbreaking projects in the self-driving car industry. He highlights the impact of the curriculum on students' careers and the innovative solutions they are developing.
"to that particular spot in time Google was the really the only main effort going on and what we believed is that it needed to happen faster and that one of the reasons it wasn't happening fast enough ..."
Oliver reveals the decision to build an actual self-driving car as part of the Udacity curriculum. He explains the motivation behind this initiative and how it serves as a practical platform for students to apply their knowledge.
"folks that I'd gotten the chance to work with him on specifically self-driving cars he likened it to getting basketball lessons from Michael Jordan which I thought was pretty fun and they were probabl..."
Oliver outlines the ambitious goal of driving a self-driving car from Mountain View to San Francisco without disengagements. He describes the challenges of navigating complex traffic conditions and the significance of this milestone.
"the curriculum that we built with some you're also welcome project to detective just like real economist people's have to do in term two you'll learn about sensor fusion localization in control this i..."
Oliver reflects on the journey of developing self-driving technology and the progress made since the inception of the curriculum. He emphasizes the importance of continuous learning and adaptation in the rapidly changing landscape of autonomous vehicles.
"turn three you'll learn about pathway and electives month and you'll learn about system integration path blending is really the brains of a self-driving car it's how the perfect here's how kind of it ..."
Cameron discusses the ambitious goal of building a self-driving car as part of Udacity's curriculum. He explains the motivation behind this initiative, aiming to prove the effectiveness of their teaching and provide students with hands-on experience in a rapidly evolving field.
"stuff so we also decided to make a curriculum extra special and we decided to do that by building an actual self-driving car and whenever I talked about this internally Udacity people asked me why why..."
Oliver outlines the milestone of driving a self-driving car from Mountain View to San Francisco, detailing the complexities of the route, including traffic lights and multi-lane roads. He highlights the team's focus on achieving this goal within a tight timeframe.
"for our self-driving car it was to drive from Mountain View to San Francisco 32 miles of driving with zero dis engagements it should be repeatable it won't be zero disengagement so every single time b..."
In this segment, Cameron recounts the early testing phases of their self-driving car project, including unexpected challenges and the iterative process of refining their technology. He shares anecdotes from testing sessions that reveal the learning curve involved in developing autonomous driving capabilities.
"outfitted a whole bunch of sensors some cameras some lighters all that good stuff we also try to build our own mount we affectionately call this the periscope I don't know why it's in slow motion but ..."
Cameron discusses the importance of real-world driving experiences in training self-driving algorithms. He reflects on the behaviors of other drivers and how these insights contributed to the development of their self-driving technology.
"believe to be a motorcycle gang and we made progress we kept iterating kept building and it started to come together in fact some stuff that we thought wouldn't work surprisingly just start to work th..."
Oliver highlights a collaboration with students to develop a traffic light classifier, showcasing the integration of machine learning into their self-driving car project. He emphasizes the significance of teamwork in overcoming technical challenges.
"we drove a little slow 25 [Music] [Music] said that was fine and pretty soon it got quite boring car was doing very well driving itself we built some cool algorithms to change lanes when necessary sim..."
Cameron shares the creative approach taken by his team to document their self-driving car journey, drawing parallels to popular media in the tech space. He reflects on the excitement and confidence gained through successful testing.
"we collaborate with some students on a traffic light classifier which was integrated into Ross there and yep pretty boring stuff so you can tell Eric was surprised that it was just fine and we also ha..."
In this segment, Oliver recounts the achievement of driving 32 miles without disengagements, discussing the significance of this milestone in the context of their self-driving car project. He reflects on the challenges faced and the progress made.
"[Music] [Music] [Music] maybe want to tow it down so it's easier because there's less traffic right this is kind of cheating and didn't count as the milestone just to be clear you'll see that we event..."
Cameron expresses his belief that the self-driving car industry is now ready for significant advancements. He discusses the technological developments that have made this possible and the potential for innovation in the field.
"[Music] [Music] and they hit it but of course that didn't count because it's in the middle of the night and that's not gonna be a very useful route but it was awesome accomplishment just to even make ..."
Oliver discusses the open-source challenges launched during his time at Udacity, focusing on the use of deep learning to predict steering angles. He highlights the collaborative efforts of students worldwide to tackle complex problems in autonomous driving.
"well we'll talk more about what this led to in a little bit let's talk about open source challenges we also got the same question why do this and it was clear to me that for something like self-drivin..."
Cameron shares insights from the diverse approaches taken by student teams in the steering angle prediction challenge. He highlights the success of one model that led to significant advancements in self-driving technology.
"again let's use this all these students from around the world to do it and we did have students from all around the world there was over a hundred teams people self organized into these little groups ..."
In this segment, Oliver discusses the challenges faced when implementing camera-only steering solutions in real-world driving scenarios. He emphasizes the importance of refining algorithms to ensure safety and reliability.
"awesome stuff and again in true voyage fashion we recorded a video of what this model perform like on our car it wasn't perfect as any first model and just that the general approach of camera only you..."
Cameron introduces Voyage, the new venture aimed at revolutionizing transportation through self-driving technology. He shares the motivation behind starting this company and the vision for a safer, more efficient transportation system.
"launching these challenges it felt like it was time for something new it was awesome to go and collaborate with all these students and it felt like you know I had to go build something so gathered tha..."
Oliver discusses the current inefficiencies in the transportation system, including safety concerns and environmental impacts. He emphasizes the need for innovative solutions to create a safer and more efficient future.
"and our goal really was that we wanted to again build a self-driving car but we wanted to do it differently we didn't want to follow the same formula that we felt we'd seen from some of the other folk..."
Cameron explains why now is the right time to build self-driving cars, citing advancements in sensor technology, computing power, and talent in the industry. He outlines the factors that contribute to the feasibility of autonomous vehicles today.
"sefa fatalities on the roads today doesn't include folks that break necks that inja break bones all that horrific stuff it's also incredibly inefficient we've again all observe this as we go about our..."
Oliver Cameron discusses the advancements in sensor technology that have made level 4 self-driving cars feasible. He highlights the improvements in resolution, range, and reliability of sensors compared to earlier models used in the DARPA challenges, emphasizing the current capabilities that enable the development of autonomous vehicles.
"and this is kind of our mission and why now why is it possible to build a self-driving car now a number of factors that we learned during that you'd ask the experience but some new as well it feels fr..."
Cameron shares his vision for the future of transportation, focusing on the potential of self-driving cars to revolutionize ride-sharing. He explains the limitations of human-driven ride-hailing services and argues that autonomous vehicles can lower costs and improve safety, ultimately transforming how people move around.
"compute is there when we you know think about the recent rise in in GPUs and whatnot finally you know being able to have enough performance in the back of a car with the power constraints that you hav..."
Oliver Cameron references Vinod Khosla's quote about market entry strategies, explaining how Voyage aims to differentiate itself in the self-driving car market. He emphasizes the importance of identifying unique opportunities, particularly in retirement communities, to avoid the pitfalls faced by other companies in the industry.
"that the optimal way for people to move around is to be able to summon a car but the thing that's suboptimal today is that you have to have a human driving you whenever you want to move around prevent..."
Cameron elaborates on why Voyage has chosen retirement communities as the initial deployment area for their self-driving technology. He discusses the slower speed limits, transportation challenges faced by residents, and the potential for improving quality of life for seniors who struggle with mobility.
"your market entry strategy is often different from your market disruption start where you find a gap in the market and push your way through and this better communicated what I mentioned at the very b..."
In this segment, Cameron introduces 'The Villages,' a large retirement community where Voyage operates. He highlights the community's size, the exclusive license for autonomous vehicle services, and the benefits of partnering with such communities to provide reliable transportation solutions for seniors.
"limits in these communities tend to be far slower than you'd see on public road much calmer roadway when you visit these locations I liken it to listening to a podcast at 0.75 X just very constrained ..."
Cameron presents statistics on the growing senior population and the vast market potential for transportation services tailored to this demographic. He emphasizes the importance of understanding the unique needs of seniors and how Voyage's services can address their transportation challenges.
"see that on you know the roads today ride-sharing on you know Public Citizen mantra is a particularly brutal battle a race to the bottom in terms of cost if we owned every retirement community in the ..."
Cameron discusses Voyage's strategic focus on self-contained communities for deploying self-driving technology. He explains the advantages of these environments, including slower speeds, simpler roadways, and the ability to work closely with community authorities to enhance service delivery.
"this is the villages whenever I show this slide people are astounded by the number of residents in a community like this over 125,000 and growing over 750 miles of road and what we have in this locati..."
In this segment, Cameron outlines Voyage's approach to sensor configuration, prioritizing performance over cost. He explains the importance of high-resolution sensors for achieving level 4 autonomy and the technical specifications of their sensor setup, including the use of advanced lidar technology.
"here and we're launching and have launched passenger services to these these residents I've got a love awesome feedback learned a lot about the needs of providing ride-sharing for senior citizens just..."
Cameron emphasizes the significance of partnerships in the self-driving ecosystem. He discusses how collaborating with other companies in areas like simulation and mapping can streamline operations and enhance the development of autonomous vehicle technology.
"cars tens of thousands of cars it plays the strengths that they have at least some patience or ability to have more extended time lines when it comes to building this technology but first up like us t..."
Cameron addresses a specific challenge in autonomous vehicle perception related to foliage. He shares examples of how other self-driving programs have struggled with detecting objects like bushes and trees, highlighting the importance of solving these perception issues for safe navigation.
"central authority these places tend to be run by private companies which makes for a quite unique relationship in a very positive way means we can deploy faster it means we have the potential to have ..."
In this segment, Cameron discusses advancements in perception technology and the importance of using neural networks for object detection. He contrasts traditional clustering algorithms with modern approaches that improve the accuracy of detecting pedestrians and other critical objects.
"hundred meters in 360 degrees many other different light hours on the vehicle to cover different certain blind spots all together we says twelve point six million points per second and then just looks..."
Oliver Cameron discusses the challenges posed by foliage in self-driving car perception systems. He explains how traditional mapping techniques can fail when dynamic objects like bushes grow outside of the mapped area, leading to potential hazards. He contrasts this with neural networks that utilize 3D scans and learned approaches to improve object detection, emphasizing the importance of accurate perception for safe navigation.
"we see going on that intends to solve those sorts of issues one of the reasons you've seen those programs including ours be particularly sensitive to foliage is because from a perception perspective o..."
Cameron highlights recent advancements in neural networks that enhance object detection capabilities in self-driving cars. He discusses various models like Pixel and VoxelNet, which improve the understanding of human features in crowded environments. This segment underscores the significance of accurate perception for better predictions and safer navigation in autonomous vehicles.
"they don't use the map as a prior instead what they do is take of course this 3d scan of the world and then take em all learned approach to the problem you'll have you know tens of thousands hundreds ..."
In this segment, Oliver Cameron shares valuable lessons learned from his experience building Voyage. He emphasizes the importance of diverse backgrounds in the self-driving industry, the need for effective team building, and the significance of being proactive rather than reactive in business. Cameron's insights provide a glimpse into the challenges and strategies of leading a tech startup in the autonomous vehicle space.
"much safer I'm also particularly fascinated by reinforcement learning which I know Alexis as well if you've read our way most recent work on imitation learning I think that's particularly cool another..."
Cameron discusses the critical aspects of building a strong team and fostering a positive company culture at Voyage. He stresses the importance of hiring the right people, being curious, and ensuring knowledge is shared across the organization. This segment highlights the challenges of scaling a startup and the necessity of adapting leadership styles as the company grows.
"came from lessons which were really really painful in the moment don't be intimidated so the thing that I feel you know happens a lot in self-driving cars is that because it started in this very acade..."
Oliver Cameron explains Voyage's strategic decision to focus on retirement communities for their self-driving car services. He recounts the influence of Sebastian Thrun's insights and the importance of understanding the unique needs of seniors. This segment explores the potential for tailored solutions that cater specifically to the elderly, emphasizing the market's significance for autonomous vehicle deployment.
"about it can jump to questions if that's helpful that was great please give a big hand [Applause] how did you identify retired communities as the target market to prioritize yes so retirement communit..."
In this segment, Cameron addresses the collateral issues related to transporting seniors in autonomous vehicles. He discusses the importance of designing user-friendly interfaces and the potential for human assistance in certain scenarios. This conversation highlights the complexities of ensuring a seamless experience for elderly passengers and the innovative solutions Voyage is exploring.
"but these are all collateral issues how do you plan to address this it's good question so the way we think about this is that today we've intentionally focused it on a segment of the market which is c..."
Cameron elaborates on the evolution of sensor technology in Voyage's self-driving vehicles. He describes the transition from first-generation to second-generation vehicles and the ongoing adjustments based on community needs and technical requirements. This segment emphasizes the importance of continuous innovation in sensor technology to enhance the performance and safety of autonomous vehicles.
"but today we focus on active adult but who knows where you go next can you talk a little bit about how you determined your final sensor sweet hmm yeah so that the truth is is never final so we think a..."
Oliver Cameron discusses the unique challenges of insurance for autonomous vehicles, highlighting the partnership with Intact Insurance. He explains how data from self-driving cars can help insurers assess risks differently compared to traditional human-driven vehicles. This segment provides insights into the evolving landscape of liability and insurance in the autonomous driving industry.
"I was curious when you showed the student LED content or when you showed one of the students in your first practice car had developed a traffic light sensor and then you showed later on that you know ..."
Cameron reflects on the initial skepticism faced when introducing self-driving technology to retirees. He shares surprising insights about their openness to autonomous vehicles, contrasting it with their slower adoption of traditional consumer technology, and discusses how familiarity with cars eases the transition.
"called intact insurance and the idea is that insurance in the autonomous age is gonna be very different than insurance you know today right for human drivers because there's different risk assessments..."
Oliver discusses the critical role of computer vision in achieving level-4 autonomy for self-driving cars. He emphasizes the importance of minimizing false negatives in perception systems and explains how combining multiple networks can enhance detection capabilities and improve overall safety.
"room for innovation there too did you have any problems like onboarding the people initially when they were like you know skeptical scared and then the other question is what are the like major missin..."
Cameron shares a fascinating perspective on how senior citizens perceive self-driving cars compared to their historical experiences with transportation. He illustrates how their life experiences shape their acceptance of new technologies, making autonomous vehicles less intimidating.
"their lives right instead of using facebook they call someone up and they have a chat you know a conversation with someone about their day or all the stuff that's going on or they you know don't share..."
Oliver elaborates on the challenges of achieving perfect perception in self-driving cars. He discusses the significance of reducing false negatives and how the integration of various perception networks can help ensure safer autonomous driving experiences.
"question was computer vision what needs to happen between now and level-4 yeah so I think the the Holy Grail right so if you had perfect perception self-driving cars are solved if we knew every object..."
Cameron addresses the implications of weather on autonomous vehicle operations, particularly during emergencies like hurricanes. He explains how remote operators monitor vehicles in real-time and the potential for advanced weather forecasting to enhance safety and operational efficiency.
"different networks have different strengths for example voxel net is particularly good at pedestrians but Pixar is not so great as pedestrians because it's from a bird's eye view where pedestrians are..."