Morteza Lahijanian

Robot regret: New research helps robots make safer decisions around humans

Jeff Zehnder — Tue, 26 Aug 2025 06:12:12 +0000

Robot regret: New research helps robots make safer decisions around humans Jeff Zehnder Tue, 08/26/2025 - 00:12

Imagine for a moment that you’re in an auto factory. A robot and a human are working next to each other on the production line. The robot is busy rapidly assembling car doors while the human runs quality control, inspecting the doors for damage and making sure they come together as they should.

Robots and humans can make formidable teams in manufacturing, health care and numerous other industries. While the robot might be quicker and more effective at monotonous, repetitive tasks like assembling large auto parts, the person can excel at certain tasks that are more complex or require more dexterity.

But there can be a dark side to these robot-human interactions. People are prone to making mistakes and acting unpredictably, which can create unexpected situations that robots aren’t prepared to handle. The results can be tragic.

New and emerging research could change the way robots handle the uncertainty that comes hand-in-hand with human interactions. Morteza Lahijanian, an associate professor in ��ñ��’s Ann and H.J. Smead Department of Aerospace Engineering Sciences, develops processes that let robots make safer decisions around humans while still trying to complete their tasks efficiently.

From left, engineering professor Morteza Lahijanian and graduate student Karan Muvvala watch as a robotic arm completes a task using wooden blocks. (Credit: Casey Cass)

In a new study presented at the International Joint Conference on Artificial Intelligence in August 2025, Lahijanian and graduate students Karan Muvvala and Qi Heng Ho devised new algorithms that help robots create the best possible outcomes from their actions in situations that carry some uncertainty and risk.

“How do we go from very structured environments where there is no human, where the robots are doing everything by themselves, to unstructured environments where there are a lot of uncertainties and other agents?” Lahijanian asked.

“If you’re a robot, you have to be able to interact with others. You have to put yourself out there and take a risk and see what happens. But how do you make that decision, and how much risk do you want to tolerate?”

Similar to humans, robots have mental models that they use to make decisions. When working with a human, a robot will try to predict the person’s actions and respond accordingly. The robot is optimized for completing a task—assembling an auto part, for example—but ideally, it will also take other factors into consideration.

In the new study, the research team drew upon game theory, a mathematical concept that originated in economics, to develop the new algorithms for robots. Game theory analyzes how companies, governments and individuals make decisions in a system where other “players” are also making choices that affect the ultimate outcome.

In robotics, game theory conceptualizes a robot as being one of numerous players in a game that it’s trying to win. For a robot, “winning” is completing a task successfully—but winning is never guaranteed when there’s a human in the mix, and keeping the human safe is also a top priority.

So instead of trying to guarantee a robot will always win, the researchers proposed the concept of a robot finding an “admissible strategy.” Using such a strategy, a robot will accomplish as much of its task as possible while also minimizing any harm, including to a human.

“In choosing a strategy, you don't want the robot to seem very adversarial,” said Lahijanian. “In order to give that softness to the robot, we look at the notion of regret. Is the robot going to regret its action in the future? And in optimizing for the best action at the moment, you try to take an action that you won't regret.”

Let’s go back to the auto factory where the robot and human are working side-by-side. If the person makes mistakes or is not cooperative, using the researchers’ algorithms, a robot could take matters into its own hands. If the person is making mistakes, the robot will try to fix these without endangering the person. But if that doesn’t work, the robot could, for example, pick up what it’s working on and take it to a safer area to finish its task.

Karan Muvvala watches the robotic arm pick up a blue block. (Credit: Casey Cass)

Much like a chess champion who thinks several turns ahead about an opponent’s possible moves, a robot will try to anticipate what a person will do and stay several steps ahead of them, Lahijanian said.

But the goal is not to attempt the impossible and perfectly predict a person’s actions. Instead, the goal is to create robots that put people’s safety first.

“If you want to have collaboration between a human and a robot, the robot has to adjust itself to the human. We don't want humans to adjust themselves to the robot,” he said. “You can have a human who is a novice and doesn't know what they're doing, or you can have a human who is an expert. But as a robot, you don't know which kind of human you're going to get. So you need to have a strategy for all possible cases.”

And when robots can work safely alongside humans, they can enhance people's lives and provide real and tangible benefits to society.

As more industries embrace robots and artificial intelligence, there are many lingering questions about what AI will ultimately be capable of doing, whether it will be able to take over the jobs that people have historically done, and what that could mean for humanity. But there are upsides to robots being able to take on certain types of jobs. They could work in fields with labor shortages, such as health care for older populations, and physically challenging jobs that may take a toll on workers’ health.

Lahijanian also believes that, when they're used correctly, robots and AI can enhance human talents and expand what we're capable of doing.

"Human-robot collaboration is about combining complementary strengths: humans contribute intelligence, judgment, and flexibility, while robots offer precision, strength, and reliability," he said.

"Together, they can achieve more than either could alone, safely and efficiently."

Off

Traditional

White

Seminar - Safe Autonomy: Are We There Yet? Unifying Learning, Control, and Decision-Making through Formal Reasoning - Oct. 4

Jeff Zehnder — Sat, 28 Sep 2024 18:00:00 +0000

Seminar - Safe Autonomy: Are We There Yet? Unifying Learning, Control, and Decision-Making through Formal Reasoning - Oct. 4 Jeff Zehnder Sat, 09/28/2024 - 12:00

Morteza Lahijanian
Assistant Professor, Smead Aerospace
Friday, Oct. 4 | 10:40 a.m. | AERO 111

Abstract: As autonomous systems become increasingly prevalent in safety-critical domains, ensuring their safe operation remains a key challenge. This seminar examines the questions: Are we there yet? Have we achieved the level of safe autonomy needed for widespread deployment? The talk will focus on integration of three foundational elements—learning, control, and decision-making—through the lens of formal reasoning.

I will discuss how machine learning enables adaptive behavior in dynamic environments, but often lacks guarantees needed for safety. Control theory provides robust frameworks for system stability but faces limitations when navigating complex, uncertain settings. Decision-making strategies offer high-level guidance, yet can struggle to align with real-world constraints. I argue that formal methods offer a powerful and critical solution to bridging these gaps, providing mathematical guarantees for system behavior while accounting for the uncertainties inherent in autonomous decision-making.

I will present our progress in unifying these approaches to enable safe autonomy, addressing both the theoretical advancements and practical challenges. Specifically, I will highlight our key contributions to enabling assured, reliable, and interactive autonomy.

Bio: Morteza Lahijanian is an assistant professor in the Aerospace Engineering Sciences department, an affiliated faculty at the Computer Science department and Robotics program, and the director of the Assured, Reliable, and Interactive Autonomous (ARIA) Systems group at the ��ñ��. He received his B.S. from the University of California, Berkeley, and his M.S. and Ph.D. in Mechanical Engineering from Boston University. He served as a postdoctoral scholar in Computer Science at Rice University. Prior to joining ��ñ��, he was a research scientist in the department of Computer Science at the University of Oxford.

Dr. Lahijanian's research interests span the areas of control theory, stochastic hybrid systems, formal methods, machine learning, and game theory with applications in robotics, particularly, motion planning, strategy synthesis, model checking, and human-robot interaction. His lab develops novel theoretical foundations and computational frameworks to enable reliable and intelligent autonomy. The emphasis is especially on safe autonomy through correct-by-construction algorithmic approaches.

As autonomous systems become increasingly prevalent in safety-critical domains, ensuring their safe operation remains a key challenge. This seminar examines the questions: Are we there yet? Have we...

Off

Traditional

White

��ñ�� lands $5.5 million Air Force project to advance orbital and AI research

Anonymous — Tue, 23 Aug 2022 15:01:46 +0000

��ñ�� lands $5.5 million Air Force project to advance orbital and AI research Anonymous (not verified) Tue, 08/23/2022 - 09:01

Jeff Zehnder

The waning gibbous Moon above the Earth's horizon over the Atlantic Ocean.

A team of ��ñ�� researchers is embarking on a major research project that will advance our understanding of orbital mechanics and monitoring, artificial intelligence, and hypersonics.

Led by Marcus Holzinger, an associate professor in the Ann and H.J. Smead Department of Aerospace Engineering Sciences, the group has signed a $5.54 million, five-year cooperative agreement with the Air Force Research Laboratory to advance science and monitoring for next generation of space vehicles – particularly those that will travel beyond low Earth orbit to the Moon.

“These are really complex multi-domain applications in the defense world and we’re bringing together preeminent researchers to tackle these problems,” Holzinger said. “There’s a real opportunity to make important advances.”

The cooperative agreement represents a significant expansion of the relationship between Smead Aerospace and the Air Force Research Laboratory’s Space Vehicles Directorate. Holzinger said the project will include ongoing collaboration and could evolve and change as the research develops.

“The region in, around, and affected by the Earth-Moon-Sun system has drastically increased in commercial activity and Department of Defense mission relevance over the last few years,” Holzinger said. “There are more and more missions going to the Moon – not just our missions but India, China, and Europe as well. That means there needs to be some sensible tracking and detection of what’s going on out there and this project addresses that crucial need directly.”

Holzinger said this area, called space domain awareness, is important for national defense and to ensure spaceflight safety and responsible behavior. Currently, the Air Force maintains tracking networks to actively catalog space vehicles to avoid collisions. However, these systems only work for spacecraft orbiting the Earth, not the Moon, and growing traffic in orbit around Earth has made collision avoidance increasingly complicated.

NASA Orbital Debris Program illustration of satellites and space debris in low Earth orbit.

To address this, the team will work to develop a framework for spacecraft to make autonomous maneuvering decisions without human input by using artificial intelligence both for collision avoidance and to execute complex tasks, said Morteza Lahijanian, an assistant professor in Smead Aerospace and a member of the project team.

“This research will teach us how to go about designing safe autonomy for complex systems, especially in a setting where multiple space vehicles need to cooperate,” said Lahijanian. “This research can lead to designing fully autonomous spacecraft that we can trust, and would eliminate the role of humans who are typically the source of errors in the design or execution of missions.”

The work also aims to better understand the unique orbital dynamics surrounding the Moon to help future researchers and commercial projects, said Holzinger.

“We’re really interested in what sorts of repeating natural orbits are best for various applications and what are the best ways to get to and from those orbits,” Holzinger said. “We want to develop design tools so mission engineers can more easily answer these questions. Right now there are not enough experts that can do that work to meet the need.”

A third goal for the cooperative agreement aims to advance the science of hypersonic vehicles. Hypersonics is an active area of research around the world for national defense purposes.

During hypersonic flight, a vehicle and the gasses surrounding it can reach thousands of degrees, triggering chemical reactions. The team hopes to develop and validate models that will ensure hypersonic vehicle signatures, heat flux, and materials response can be predicted with minimal uncertainty.

In addition to Holzinger and Lahijanian, additional ��ñ�� faculty partners include professors Natasha Bosanac, Tim Minton, Hanspeter Schaub, and Dan Scheeres.

A team of ��ñ�� researchers is embarking on a major research project that will advance our understanding of orbital mechanics and monitoring, artificial intelligence, and hypersonics. Led by Marcus Holzinger, an...

Off

Traditional

White

Research In Focus: How Morteza Lahijanian Creates Safety and Soundness in Autonomous Systems

Anonymous — Mon, 13 Dec 2021 22:21:51 +0000

Research In Focus: How Morteza Lahijanian Creates Safety and Soundness in Autonomous Systems Anonymous (not verified) Mon, 12/13/2021 - 15:21

Assistant Professor Morteza Lahijanian’s work is at the intersection of safety and soundness in robotics, focusing on developing autonomous systems which operate safely and effectively alongside humans to help improve the well-being of individuals and societies.

As the Director of the Assured Reliable Interactive Autonomous (ARIA) Systems Group, Lahijanian oversees nine PhD students in computational and experimental work honing correct-by-construction algorithmic approaches to robotic systems.

Watch to learn more about Morteza and ARIA’s work:

[video:https://www.youtube.com/watch?v=r9DUImCrx18]

Off

Traditional

White

NSF grants aim to improve security and safety of autonomous cars and systems

Anonymous — Fri, 30 Oct 2020 15:43:29 +0000

NSF grants aim to improve security and safety of autonomous cars and systems Anonymous (not verified) Fri, 10/30/2020 - 09:43

Researchers at ��ñ�� are leading four new NSF-funded projects that are exploring the safety and security of autonomous systems, including those used in self-driving vehicles.

The work is part of an international effort to address the significant safety and security obstacles to widespread adoption of these systems in the very near future.

Assistant Professor Majid Zamani is leading several of these projects within the Department of Computer Science. He is also part of the Autonomous Systems Interdisciplinary Research Theme in the college. He said this cluster of projects all address safety and security but embrace and apply knowledge from different fields such as control theory, formal methods and machine learning.

“One of the projects looks at how to prevent outside intruders from gaining private information about autonomous systems through their sensor measurements,” Zamani said. “Another ensures the actual auto-pilot systems–the embedded control software–work safely as intended, both in calm and warm days in Arizona and in snowy weather in Michigan, by embracing ideas from transfer learning.”

Assistant Professor Ashutosh Trivedi is also heavily involved in the work, leading one of the projects that looks at machine learning techniques for creating foolproof safety systems. A member of the research theme as well, he said the answers that will come out of this kind of work over the next three years will have many applications for aerospace systems and more tangible aspects of everyday life.

“The safety and security of cyber-physical systems will eventually go well beyond the autonomous cars we are working with here,” Trivedi said. “These systems are the technological backbone of the increasingly interconnected and smart world where a design fault or security vulnerability can be catastrophic to the system, to the user or to those around them. This work has implications for wearable and implantable medical devices, smart infrastructure and connected communities, to name only a few areas.”

Here are the project details including staffing and funding totals:

Project Title: CPS: Medium: Correct-by-Construction Controller Synthesis using Gaussian Process Transfer Learning
Principal Investigator: Majid Zamani, Department of Computer Science
Co-Principal Investigators: Morteza Lahijanian and Eric Frew, Department of Aerospace Engineering Sciences
Amount: $1,200,000
��ñ��: This project explores improvements to embedded control software for safety-critical cyber-physical systems in autonomous vehicles. Embedded control software forms the main core of autonomous systems wherein software components interact with physical systems such as traffic networks and power networks to name a few. These systems often have complex dynamics that are difficult to predict and ensure when it comes to safe operation. This project investigates a novel correct-by-construction controller synthesis scheme for these systems by embracing ideas from Gaussian processes. If successful, this could allow safety controllers developed for one type of autonomous vehicle to be transferred to another of a wholly new type – or for use in a new environment all together ¬– while still ensuring the original safety guarantee. This would save time on production and will be tested on underwater and aerial vehicles with an eye to future applications outside of self-driving cars.

Project Title: Secure-by-Construction Controller Synthesis for Cyber-Physical Systems
Principal Investigator: Majid Zamani, Department of Computer Science
Co-Principal Investigator: Ashutosh Trivedi, Department of Computer Science
Amount: $387,640
��ñ��: The security of autonomous vehicles from outside intruders is a new and growing area of research which has previously lagged behind more obvious safety concerns around the car’s actual operation. But because these vehicles collect and use a tremendous amount of personal data, they are appealing targets for hackers who can intrude through internet connected systems or other linked personal devices. From there they can deduce private internal information such as destination history or even potentially tamper with the vehicle. The proposed research aims to address this in parallel with the physical safety of the vehicle on the road. The ultimate goal is to develop algorithmic techniques and computational tools for constructing discrete controllers guaranteeing both safety and privacy properties, which are then automatically refined as hybrid controllers for the original systems. Doing would speed up overall development as security features would not have to be added on after the systems are already fully designed. This should also allow for more overlapping protection in both the physical and security arenas.

Project Title: SHF: Small: Omega-Regular Objectives for Model-Free Reinforcement Learning
Principal Investigator: Ashutosh Trivedi, Department of Computer Science
Co-Principal Investigator: Fabio Somenzi, Department of Electrical, Computer and Energy Engineering
Amount: $500,000
��ñ��: In reinforcement learning, software agents rely on and receive rewards that promote the achievement of given objectives or tasks. Scalar rewards can be used to reinforce the desired behavior, like keeping the car on the road and between the lines or withheld when drifting out of bounds. This machine learning technique has been demonstrated to be effective in many autonomous systems such as self-driving cars and manufacturing systems as well as other aspects of modern life such as social networks and internet connected devices. However, their integration into safety-critical settings for self-driving cars requires a new set of methods to ensure the decisions they ultimately make are the right ones. This project develops a rigorous approach to the design and verification of reinforcement learning-enabled systems that addresses issues of safety, efficiency, and scalability. This project also aims to develop an open source tool to create reinforcement learning algorithms to that end.

Project Title: An Entropy Approach to Invariance and Reachability of Uncertain Control Systems with Limited Information
Individual Principal Investigator: Majid Zamani, Department of Computer Science
Amount: $379,327
��ñ��: This project explores how autonomous vehicles can cope with limited bandwidth while interacting with cloud-based servers to share information and at the same time ensure their physical safety. Currently, communication systems, digital sensors, and microprocessors are being used by the car’s embedded control systems to respond to the needs and requests of external traffic network or the needs of the internal engine control for example. The interplay between those safety and reliability requirements – and the car’s ability to respect or enforce them – is key to keeping the vehicle safe on the road. While possible now, there is a finite amount of communication bandwidth available for maintaining that balance and the number of cars looking to use it is expected to go up over time. This research aims to establish the fundamental minimum data rates – or bandwidth – needed to make sure that the safety of the vehicles are not compromised. The results of this project will also enable the first step towards the efficient deployment of many innovative applications including underwater vehicles, sensor networks, and industrial control networks.

Off

Traditional

White

Beyond mundane: Lahijanian’s work in safety-critical systems pushes autonomy forward

Anonymous — Mon, 10 Feb 2020 23:17:38 +0000

Beyond mundane: Lahijanian’s work in safety-critical systems pushes autonomy forward Anonymous (not verified) Mon, 02/10/2020 - 16:17

After decades of work to make robots more and more capable of helping humans, robotic systems have become ever-present in our daily lives, helping with tasks big and small.

But it’s what the next decade of research may hold that inspires and motivates Assistant Professor Morteza Lahijanian.

“To have long-term autonomy, we need to understand how humans and robots interact better,” said Lahijanian, who is an assistant professor in the Ann and H.J. Smead Department of Aerospace Engineering Sciences. “Understanding what happens when we deploy these systems into our society–that is the important work to come.”

Lahijanian joined Smead Aerospace in 2018 after time as a research scientist in the University of Oxford’s Computer Science Department. Before that, he served as a postdoctoral researcher at Rice University following completion of his PhD in mechanical engineering from Boston University. His research focuses on safety and soundness–with an emphasis on safe autonomy–through correct-by-construction algorithmic approaches.

In correct-by-construction design, engineers create models before creating code. The resulting product is then used to understand and create solutions to problems like the safe operation of autonomous vehicles, with verification being implicitly embedded in the design process – ensuring the correct behavior happens at the correct time for a specific situation. Testing is still performed, but its role is only to validate the model.

Lahijanian said his work is focused mainly on algorithmic design, helping robots and humans achieve a goal either through an effective collaboration or a solo performance of the robot despite model uncertainty.

“That means trying to figure out what robots should do when following instructions from humans,” he said. “What does the robot need to understand from the human to get the task done correctly? How does the robot react if the human makes a mistake?”

Since coming to ��ñ��, Lahijanian has joined several projects and made connections through the Autonomous Systems Interdisciplinary Research Theme. One of those projects centers on enabling long-term marine robotic autonomy. He said the project focuses on learning specifications for autonomous navigation and interaction for submarines. Specifically: learning what a human operator wants an autonomous submarine to do.

Lahijanian working through a problem with a student in the new aerospace engineering sciences facility.

He selected that topic because the underwater environment brings a unique set of challenges that haven’t been solved yet.

“It’s hard to send data, and there are problems using sensors underwater, resulting in a highly uncertain environment,” he said. “We developed a scenario where a human is exploring. The mission can be very complex–maybe studying a school of fish. The robot could learn from the human’s actions doing this and eventually take over some of the low-level tasks like avoiding the seabed or not getting too close to the fish. Slowly improving at that over time and eventually taking over would free the human up for other tasks.”

Lahijanian said the IRT was instrumental in coming up with a good idea and providing funding to pursue it in the early stages.

“I am housed in aerospace, but I don’t feel disconnected from my colleagues and collaborators. Through the IRT I was encouraged to talk with other faculty, and that resulted in an interesting problem working with people from all different backgrounds,” he said. “I knew I didn’t have knowledge of all fields I wanted to get to, and the IRT has been great for connecting me to the people who do.”

Off

Traditional

White

Welcome to our new Smead Aerospace Faculty

Anonymous — Tue, 11 Sep 2018 14:15:04 +0000

Welcome to our new Smead Aerospace Faculty Anonymous (not verified) Tue, 09/11/2018 - 08:15

Jeff Zehnder

Who are our new faculty?

They are researchers, educators, and business leaders.
Bring the department new research opportunities and partnerships.
Have diverse backgrounds and come to Boulder from near and far.
Are proud additions to the Smead Aerospace and CU Buffs family.

Off

Traditional

White

Morteza Lahijanian

Robot regret: New research helps robots make safer decisions around humans

Off

Seminar - Safe Autonomy: Are We There Yet? Unifying Learning, Control, and Decision-Making through Formal Reasoning - Oct. 4

Off

��ñ���� lands $5.5 million Air Force project to advance orbital and AI research

Off

Research In Focus: How Morteza Lahijanian Creates Safety and Soundness in Autonomous Systems

Off

NSF grants aim to improve security and safety of autonomous cars and systems

Off

Beyond mundane: Lahijanian’s work in safety-critical systems pushes autonomy forward

Off

Welcome to our new Smead Aerospace Faculty

Off

��ñ�� lands $5.5 million Air Force project to advance orbital and AI research