There has been a shift from fully autonomous cars to advanced driver assistance systems (ADAS), such as Tesla's autopilot, which are more profitable and provide value. AI advancements have significantly boosted the reliability and performance of these systems, leading to a resurgence of interest in the technology.
AI has revolutionized the design and implementation of autonomous systems by enabling the use of foundation models, which bring generalist knowledge from internet-scale data to the task of autonomous driving. This reduces the need for vehicle-specific data and improves performance, especially in handling rare or unusual driving scenarios.
People generally adapt quickly to the experience of riding in autonomous vehicles, feeling natural after the initial awe. However, in systems like Tesla's autopilot, keeping users engaged and informed about the technology's limitations is crucial to ensure safety and trust.
The challenges include cybersecurity risks, cost of setting up communication infrastructure, and the competitive environment among manufacturers. As a result, many companies focus on internal data processing rather than relying on real-time communication with other vehicles or infrastructure.
Risk-averse planning ensures safety by treating it as a constraint rather than an objective. Safety requirements are based on the severity and exposure of potential failures, and systems are designed and validated to meet these requirements statistically, providing a provable level of safety.
Autonomous systems are essential for tasks like building lunar outposts, exploring icy bodies in the solar system, and managing space debris. AI is playing a significant role in designing these systems, especially for missions where human presence is impractical or impossible.
Space is becoming increasingly crowded with satellites and debris, much of which does not communicate or cooperate. Autonomous systems must navigate this environment while ensuring collision avoidance, which is a significant technical challenge.
Distributed systems are more cost-effective and provide better coverage than monolithic architectures. They also enable collaboration among multiple vehicles, improving accuracy and efficiency in tasks like landing on the moon or Mars.
Private companies like SpaceX have introduced miniaturized space assets, making space missions more affordable and opening up new business opportunities. This has led to a proliferation of private stakeholders in the space sector, focusing on applications like communication, surveillance, and logistics.
Returning guest Marco Pavone) is an expert in autonomous robotic systems, such as self-driving cars and autonomous space robots. He says that there have been major advances since his last appearance on the show seven years ago, mostly driven by leaps in artificial intelligence. He tells host Russ Altman) all about the challenges and progress of autonomy on Earth and in space in this episode of Stanford Engineering’s The Future of Everything podcast.
Have a question for Russ? Send it our way in writing or via voice memo, and it might be featured on an upcoming episode. Please introduce yourself, let us know where you're listening from, and share your quest. You can send questions to [email protected]).
Episode Reference Links:
Connect With Us:
Chapters:
(00:00:00) Introduction
Russ Altman introduces guest Marco Pavone, a professor of aeronautics and astronautics at Stanford.
(00:02:37) Autonomous Systems in Everyday Life
Advancements in the real-world applications of autonomous systems.
(00:03:51) Evolution of Self-Driving Technologies
The shift from fully autonomous cars to advanced driver assistance systems.
(00:06:36) Public Perception of Autonomous Vehicles
How people react to and accept autonomous vehicles in everyday life.
(00:07:49) AI’s and Autonomous Driving
The impact of AI advancements on autonomous driving performance.
(00:09:52) Simulating Edge Cases for Safety
Using AI to simulate rare driving events to improve safety and training.
(00:12:04) Autonomous Vehicle Communication
Communication challenges between autonomous vehicles and infrastructure.
(00:15:24) Risk-Averse Planning in Autonomous Systems
How risk-averse planning ensures safety in autonomous vehicles.
(00:18:43) Autonomous Systems in Space
The role of autonomous robots in space exploration and lunar missions.
(00:22:47) Space Debris and Collision Avoidance
The challenges of space debris and collision avoidance with autonomous systems.
(00:24:39) Distributed Autonomous Systems for Space
Using distributed autonomous systems in space missions for better coordination.
(00:28:40) Conclusion
Connect With Us:
Episode Transcripts >>> The Future of Everything Website)
Connect with Russ >>> Threads) / Bluesky) / Mastodon)
Connect with School of Engineering >>>Twitter/X) / Instagram) / LinkedIn) / Facebook)