Robotics

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

Jeff Zehnder — Fri, 29 Aug 2025 16:28:28 +0000

Robot regret: New research helps robots make safer decisions around humans Jeff Zehnder Fri, 08/29/2025 - 10:28

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 ��’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

Achey earns Department of Defense NDSEG fellowship

Charles Ferrer — Tue, 26 Aug 2025 19:14:38 +0000

Achey earns Department of Defense NDSEG fellowship Charles Ferrer Tue, 08/26/2025 - 13:14

Lorin Achey, a second-year computer science PhD student, has earned the prestigious 2025 National Defense Science and Engineering Graduate Fellowship for her promising research in robotic perception systems. The Department of Defense fellowship was established to recognize and support science and engineering PhD students in disciplines of military importance.

Off

Traditional

White

‘Cyborg jellyfish’ could aid in deep-sea research, inspire next-gen underwater vehicles

Alexander James Servantez — Wed, 20 Aug 2025 20:36:07 +0000

‘Cyborg jellyfish’ could aid in deep-sea research, inspire next-gen underwater vehicles Alexander Jame… Wed, 08/20/2025 - 14:36

Assistant Professor Nicole Xu first became fascinated with moon jellyfish more than a decade ago because of their extraordinary swimming abilities. Today, Xu has developed a way to harness their efficiency and ease at moving through the water in ways that could make some types of aquatic research much easier.

Off

Traditional

White

Researchers testing next-generation ankle braces for stroke survivors

Alexander James Servantez — Tue, 15 Jul 2025 21:10:47 +0000

Researchers testing next-generation ankle braces for stroke survivors Alexander Jame… Tue, 07/15/2025 - 15:10

Nearly 80% of all stroke survivors experience walking issues and turn to ankle braces for increased support, but ankle braces are still very limited and many stroke survivors report no improvements when using them. Assistant Professor Cara Welker is leading a new, collaborative research project that aims to transform the way these assistive devices are designed.

Off

Traditional

White

Robots and chemistry isn’t just a fun combo. Bruns says it’s the future

Alexander James Servantez — Fri, 06 Jun 2025 22:30:26 +0000

Robots and chemistry isn’t just a fun combo. Bruns says it’s the future Alexander Jame… Fri, 06/06/2025 - 16:30

Assistant Professor Carson Bruns is leading the charge on an NSF-funded project that he and his team like to call "robochemistry." Their goal is to create robotic sidekicks that can assist chemists with burdensome or unsafe tasks that they may routinely encounter in a wet lab. But that's not all: this unique blend of bots and beakers can also inspire youth interest in science.

Off

Traditional

White

Tiny robot team could be a gamechanger for safety inspections

Alexander James Servantez — Wed, 21 May 2025 20:01:24 +0000

Tiny robot team could be a gamechanger for safety inspections Alexander Jame… Wed, 05/21/2025 - 14:01

Assistant Professor Kaushik Jayaram, in collaboration with Laura Blumenschein, has received a $1.4 million grant from the U.S. Air Force Research Laboratory to develop a tiny robot super team capable of navigating a complex maze of machinery and squeeze through the tightest of spaces—like the guts of a jet engine—to potentially perform non-destructive evaluation faster, cheaper and better than ever before.

Off

Traditional

White

Engineer nabs prestigious grants to design insect-inspired, shapeshifting robots

Alexander James Servantez — Wed, 30 Apr 2025 21:52:07 +0000

Engineer nabs prestigious grants to design insect-inspired, shapeshifting robots Alexander Jame… Wed, 04/30/2025 - 15:52

Assistant Professor Kaushik Jayaram of the Paul M. Rady Department of Mechanical Engineering is the recipient of a $650,000 CAREER award from the U.S. National Science Foundation. The funding will help Jayaram make advancements in robots by drawing from what might seem to be an unlikely source: insects and other small creatures.

Off

Traditional

White

Robotics research to help strengthen domestic battery supply chain

Emily Adams — Thu, 05 Dec 2024 18:16:48 +0000

Robotics research to help strengthen domestic battery supply chain Emily Adams Thu, 12/05/2024 - 11:16

Computer scientist Nikolaus Correll and his lab have been awarded $1.8 million by the U.S. Department of Energy Advanced Research Projects Agency-Energy (ARPA-E) to help establish a circular supply chain for domestic electric vehicle (EV) batteries.

Off

Traditional

White

Robotics in action: CU Engineering demonstrates interdisciplinary research at showcase

Anonymous — Thu, 24 Oct 2024 21:33:11 +0000

Robotics in action: CU Engineering demonstrates interdisciplinary research at showcase Anonymous (not verified) Thu, 10/24/2024 - 15:33

Caroline Harrah

Standing-room-only event was part of ��’s annual Research & Innovation Week held Oct. 14-18

The College of Engineering & Applied Science welcomed a packed audience to its Robotics Showcase on Oct. 17. The standing-room-only event, part of ��’s annual Research & Innovation Week, drew students, faculty and robotics enthusiasts, including middle and high school students and the general public, eager to explore the latest advancements in research shaping the future of the field.

The event emphasized the interdisciplinary nature of CU’s robotics research, showcasing collaborations across electrical, computer and energy engineering; mechanical engineering; aerospace engineering sciences; and computer science to tackle complex societal challenges.

Attendees were treated to demonstrations of bio-inspired robots (Kaushik Jayaram and Nicole Xu), autonomous drone systems (Nisar Ahmed), robots with human-like dexterity (Nikolaus Correll), and robot skin technology (Alessandro Roncone), as well as Boston Dynamics’ Spot. The demos highlighted technologies poised to transform fields such as search and rescue, deep-sea exploration and industrial maintenance in challenging environments, while improving human-robot capabilities and interactions.

In addition to the research on display, CU Engineering introduced its new graduate degrees in robotics— two master’s programs (Master of Science in Robotics thesis option and Master of Science in Robotics nonthesis option) and a PhD in Robotics—launched in 2023. These programs offer students immersive, hands-on research opportunities that engage them with the technologies featured at the showcase, preparing them to lead in the evolving robotics landscape.

CU Engineering’s Research Support Office extends its thanks to all the participants who made the event a success. For more details, check out media coverage by the Boulder Daily Camera in the article “Take Humans Out of Dangerous Equations: �� Showcases its Progress in Robots” and Denver7’s “�� Hosts Robotics Showcase to Celebrate Research & Innovation Week,” which spotlight ��’s leadership in robotics research and innovation.

Showcase Highlights

The Robotics Showcase featured a range of innovative research that exemplifies ��’s interdisciplinary collaboration and commitment to addressing real-world problems. Highlights included:

Shape-Morphing Insect-Scale Robots
Kaushik Jayaram (ME, Robotics)
Hari Hari Prasad presented insect-scale robots capable of changing shape to adapt to their environment. These shape-shifting systems demonstrate agility and adaptability, essential for real-world applications in challenging environments.
Human-Centered Autonomy for Dynamic sUAS Target Search Operations
Nisar Ahmed (AERO, Robotics)
Hunter Ray demonstrated advances in autonomous drone systems that enhance collaboration with human operators. These drones are designed for search and rescue missions, leveraging real-time data from operators to improve decision-making.
Open World Manipulation
Nikolaus Correll (CS, Robotics)
William Xie demonstrated robots with human-like dexterity, integrating sensors, actuators, and communication capabilities into composite materials to create robots that mimic the functionality of muscles, skin, and bones.
Bioinspired and Biohybrid Robotics
Nicole Xu (ME, Robotics)
Yunxing Su demonstrated research on aquatic robots for environmental monitoring. These robots combine natural and engineered designs to create energy-efficient, maneuverable systems for tracking climate change.
Robot Skin and Dynamic Human-Robot Interaction
Alessandro Roncone (CS, Robotics)
Dusty Woods, Caleb Escobedo and Claire Lohrmann demonstrated robot skin technology that enhances human-robot interactions. These modular sensor units, placed on robot manipulators, enable robots to safely and intuitively respond to external contact.
NSF IUCRC Center for Aerial Autonomy, Mobility, and Sensing (CAAMS)
Zachary Sunberg (AERO, Robotics)
Sunberg’s lab demonstrated autonomous drones in wilderness search and rescue operations. By integrating human operators into the decision-making process, these drones improve the efficiency and safety of missions in remote environments.

CU Engineering welcomed a packed audience to its Robotics Showcase on Oct. 17. The event, part of ��’s annual Research & Innovation Week, drew students, faculty and robotics enthusiasts, including middle and high school students and the general public, eager to explore the latest advancements in research shaping the future of the field.

Off

Traditional

White