Latest News

Upcoming Events

Apr
2
Tue
MechE/LCSR/IAA Seminar: Benjamin Riviere, “What Do Robots Dream of? Search-Based Decision-Making and Control of Continuous Systems” @ Malone Hall 228, Johns Hopkins University
Apr 2 @ 3:00 pm – 4:00 pm

Benjamin Riviere.

Title: “What Do Robots Dream of? Search-Based Decision-Making and Control of Continuous Systems”

Abstract:What do robots dream of? My research seeks answers to this question by designing how robots simulate the effect of their actions on the future, and how they use that information to make intelligent decisions. This is formalized in a tree-search framework that solves new decision-making and control problems in real-time, provides optimality and stability guarantees, and synergizes with deep learning. However, search requires a discrete space, and therefore its application to the high-dimensional continuous world of physical robots presents challenges. In this talk, I will discuss advances in three key areas: (i) search with complex dynamics applied to a quadrotor navigating a windy arena of moving obstacles, (ii) search with uncertainty applied to a spacecraft with faulty components that must simultaneously diagnose its state and maintain safety, and (iii) search for N-player differential games applied to a swarm of quadrotors coordinating and competing for objectives.

Bio: Benjamin Riviere is a PhD student at the California Institute of Technology, advised by Prof. Soon-Jo Chung. He received the B.S. in Mechanical Engineering from Stanford University in 2017 and the M.S. in Aeronautics from Caltech in 2018. His research interests are at the intersection of search-based planning, machine-learning, and dynamical systems with applications in robotics, space autonomy, and self-driving cars. He has received multiple awards including Honorable Mention for Best Paper at IEEE RA-L and Best Graduate Student GNC paper at AIAA Scitech, and was selected as an RSS Pioneer and a Microsoft Future Leader in Robotics and AI.

Website: https://me.jhu.edu/event/meche-lcsr-iaa-seminar-ben-riviere-from-california-institute-of-technology/

Zoom: https://wse.zoom.us/j/95583667779
Meeting ID 955 8366 7779
Passcode 530803

Apr
10
Wed
MechE/IAA Seminar: Dr. Glen Chou, “Toward End-to-end Reliable Robot Learning for Autonomy and Interaction” @ Hackerman Hall B-17, Johns Hopkins University
Apr 10 @ 12:00 pm – 1:00 pm

Glen Chou.

Title: “Toward End-to-end Reliable Robot Learning for Autonomy and Interaction”

Abstract: Robots must behave safely and reliably if we are to confidently deploy them in the real world around humans. To complete tasks, robots must manage a complex, interconnected autonomy stack of perception, planning, and control software. While machine learning has unlocked the potential for full-stack end-to-end control in the real world, these methods can be catastrophically unreliable. In contrast, model-based safety-critical control provides rigorous guarantees, but struggles to scale to real systems, where common assumptions, e.g., perfect task specification and perception, break down.

However, we need not choose between real-world utility and safety. By taking an end-to-end approach to safety-critical control that builds and leverages knowledge of where learned components can be trusted, we can build practical yet rigorous algorithms that can make real robots more reliable. I will first discuss how to make task specification easier and safer by learning hard constraints from human task demonstrations, and how we can plan safely with these learned specifications despite uncertainty. Then, given a task specification, I will discuss how we can reliably leverage learned dynamics and perception for planning and control by estimating where these learned models are accurate, enabling probabilistic guarantees for end-to-end vision-based control. Finally, I will provide perspectives on open challenges and future opportunities in assuring algorithms for space autonomy, including robust perception-based hybrid control algorithms for reliable data-driven robotic manipulation and human-robot collaboration.

Bio: Glen Chou is a postdoctoral associate at MIT CSAIL, advised by Prof. Russ Tedrake. His research focuses on end-to-end safety and reliability guarantees for learning-enabled robots that operate around humans. Previously, Glen received his PhD in Electrical and Computer Engineering from the University of Michigan in 2022, where he was advised by Profs. Dmitry Berenson and Necmiye Ozay. Prior to that, he received dual B.S. degrees in Electrical Engineering and Computer Science and Mechanical Engineering from UC Berkeley in 2017. He is a recipient of the National Defense Science and Engineering Graduate (NDSEG) fellowship, the NSF Graduate Research fellowship, and is a Robotics: Science and Systems Pioneer.

Website: https://me.jhu.edu/event/meche-iaa-seminar-dr-glen-chou-from-massachusetts-institute-of-technology/

Zoom: https://wse.zoom.us/j/95583667779
Meeting ID 955 8366 7779
Passcode 530803

Apr
16
Tue
IAA Seminar Series – Tom Dietterich
Apr 16 @ 10:45 am – 11:45 am

Details coming soon.

May
21
Tue
IAA Seminar Series – Tianmin Shu
May 21 @ 10:45 am – 11:45 am

Details coming soon.

How Do We Create an Assured Autonomous Future?

Autonomous systems have become increasingly integrated into all aspects of every person’s daily life. In response, the Johns Hopkins Institute for Assured Autonomy (IAA) focuses on ensuring that those systems are safe, secure, and reliable, and that they do what they are designed to do.

Pillars of the IAA

Technology

Autonomous technologies perform tasks with a high degree of autonomy and often employ artificial intelligence (AI) to simulate human cognition, intelligence, and creativity. Because these systems are critical to our safety, health, and well-being as well as to the fabric of our system of commerce, new research and engineering methodologies are needed to ensure they behave in safe, reasonable, and acceptable ways…

Ecosystem

Autonomous systems must integrate well with individuals and with society at large. Such systems often integrate into—and form collectively into—an autonomous ecosystem. That ecosystem—the connections and interactions between autonomous systems, over networks, with the physical environment, and with humans—must be assured, resilient, productive, and fair in the autonomous future…

Ethics and Governance

The nation must adopt the right policy to ensure autonomous systems benefit society. Just as the design of technology has dramatic impacts on society, the development and implementation of policy can also result in intended and unintended consequences. Furthermore, the right governance structures are critical to enforce sound policy and to guide the impact of technology…

  • In recent years, we have learned that the most important element about autonomous systems is – for humans – trust. Trust that the autonomous systems will behave predictably, reliably, and effectively. That sort of trust is hard-won and takes time, but the centrality of this challenge to the future of humanity in a highly autonomous world motivates us all.
    Ralph Semmel, Director, Applied Physics Laboratory
  • In the not too distant future we will see more and more autonomous systems operating with humans, for humans, and without humans, taking on tasks that were once thought of as the exclusive domains of humans. How can we as individuals and as a society be assured that these systems are design for resilience against degradation or malicious attack? The  mission of the Institute is to bring assurance to people so that as our world is populated by autonomous systems they are operating safely, ethically, and in the best interests of humans.
    Ed Schlesinger Benjamin T. Rome Dean, Whiting School of Engineering