Researchers are developing better, faster ways of providing human guidance to autonomous robots.
Told to optimize for speed while racing down a track in a computer game, a car pushes the pedal to the metal … and proceeds to spin in a tight little circle. Nothing in the instructions told the car to drive straight, and so it improvised.
This example – funny in a computer game but not so much in life – is among those that motivated Stanford University researchers to build a better way to set goals for autonomous systems.
Dorsa Sadigh, assistant professor of computer science and of electrical engineering, and her lab have combined two different ways of setting goals for robots into a single process, which performed better than either of its parts alone in both simulations and real-world experiments. The researchers presented the work June 24 at the Robotics: Science and Systems conference.
“In the future, I fully expect there to be more autonomous systems in the world and they are going to need some concept of what is good and what is bad,” said Andy Palan, graduate student in computer science and co-lead author of the paper. “It’s crucial, if we want to deploy these autonomous systems in the future, that we get that right.”
The team’s new system for providing instruction to robots – known as reward functions – combines demonstrations, in which humans show the robot what to do, and user preference surveys, in which people answer questions about how they want the robot to behave.
“Demonstrations are informative but they can be noisy. On the other hand, preferences provide, at most, one bit of information, but are way more accurate,” said Sadigh. “Our goal is to get the best of both worlds, and combine data coming from both of these sources more intelligently to better learn about humans’ preferred reward function.”
Demonstrations and surveys
In previous work, Sadigh had focused on preference surveys alone. These ask people to compare scenarios, such as two trajectories for an autonomous car. This method is efficient, but could take as much as three minutes to generate the next question, which is still slow for creating instructions for complex systems like a car.
To speed that up, the group later developed a way of producing multiple questions at once, which could be answered in quick succession by one person or distributed among several people. This update sped the process 15 to 50 times compared to producing questions one-by-one.
The new combination system begins with a person demonstrating a behavior to the robot. That can give autonomous robots a lot of information, but the robot often struggles to determine what parts of the demonstration are important. People also don’t always want a robot to behave just like the human that trained it.
“We can’t always give demonstrations, and even when we can, we often can’t rely on the information people give,” said Erdem Biyik, a graduate student in electrical engineering who led the work developing the multiple-question surveys. “For example, previous studies have shown people want autonomous cars to drive less aggressively than they do themselves.”
That’s where the surveys come in, giving the robot a way of asking, for example, whether the user prefers it move its arm low to the ground or up toward the ceiling. For this study, the group used the slower single question method, but they plan to integrate multiple-question surveys in later work.
In tests, the team found that combining demonstrations and surveys was faster than just specifying preferences and, when compared with demonstrations alone, about 80 percent of people preferred how the robot behaved when trained with the combined system.
“This is a step in better understanding what people want or expect from a robot,” said Sadigh. “Our work is making it easier and more efficient for humans to interact and teach robots, and I am excited about taking this work further, particularly in studying how robots and humans might learn from each other.”
Better, faster, smarter
People who used the combined method reported difficulty understanding what the system was getting at with some of its questions, which sometimes asked them to select between two scenarios that seemed the same or seemed irrelevant to the task – a common problem in preference-based learning. The researchers are hoping to address this shortcoming with easier surveys that also work more quickly.
“Looking to the future, it’s not 100 percent obvious to me what the right way to make reward functions is, but realistically you’re going to have some sort of combination that can address complex situations with human input,” said Palan. “Being able to design reward functions for autonomous systems is a big, important problem that hasn’t received quite the attention in academia as it deserves.”
The team is also interested in a variation on their system, which would allow people to simultaneously create reward functions for different scenarios. For example, a person may want their car to drive more conservatively in slow traffic and more aggressively when traffic is light.
Learn more: Stanford researchers teach robots what humans want
The Latest on: Autonomous systems
[google_news title=”” keyword=”autonomous systems” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Autonomous systems
- Chemists develop highly reflective black paint to make objects more visible to autonomous carson May 2, 2024 at 6:12 am
Driving at night might be a scary challenge for a new driver, but with hours of practice it soon becomes second nature. For self-driving cars, however, practice may not be enough because the lidar ...
- Shhh! 3 Secret Autonomous Driving Stocks Flying Below Wall Street’s Radaron May 2, 2024 at 3:00 am
InvestorPlace - Stock Market News, Stock Advice & Trading Tips While a high-risk, high-reward sector, autonomous driving stocks represent a ...
- Autonomous agtech robotics startup nabs funding as it gears up for expansionon May 1, 2024 at 10:10 am
FarmWise has been focused on serving farmers in California and Arizona and is gearing up to expand into more regions across the U.S.
- Are autonomous weapons a source of dehumanization?on May 1, 2024 at 4:48 am
A two-day conference on the topic of autonomous weapons systems was hosted by the Austrian government, where military technology experts and delegates from 143 countries gathered to discuss the impact ...
- DARPA's autonomous 'Manta Ray' drone can glide through ocean depths undetectedon May 1, 2024 at 12:00 am
Engineers have assembled an autonomous underwater drone that the U.S. Defense Advanced ... the vice president of naval and oceanic systems at Northrop Grumman, wrote in a LinkedIn post resharing the ...
- Autonomous weapons reduce moral agency and devalue human lifeon April 30, 2024 at 8:40 pm
Military technology experts gathered in Vienna have warned about the detrimental psychological effects of AI-powered weapons, arguing that implementing systems of algorithmic-enabled killing dehumanis ...
- Inside the Autonomous Racing League event that pitted a self-driving car against a Formula 1 driveron April 30, 2024 at 8:17 am
Modern teams are awash in real-time digital feedback from the cars. The A2RL, as it is known, is not the first autonomous racing series: There's the Roborace series, which saw autonomous race cars ...
- Neusoft Reach and Ambarella Forge Strategic Partnership to Drive Advancements in Autonomous Driving and Intelligent Automotive Technologyon April 30, 2024 at 4:00 am
Photo: From left to right, Yongfeng Wang, chairman of Neusoft Reach; Wei Lius, deputy general manager of Neusoft Reach; Nick Kong, senior director of Greater China business development at Ambarella; ...
- - The Battle for Autonomous Driving: Can Musk Outsmart China's Tech Giants?on April 30, 2024 at 1:15 am
In China, the world's largest car market, Tesla's "Full Self-Driving" (FSD) system may be on the verge of a significant breakthrough in the international race for autonomous vehicles, reports Reuters.
- More speed required in regulating autonomous weapons systemson April 29, 2024 at 5:00 pm
At the same time, calls for a binding treaty banning certain autonomous weapons systems are growing louder. In addition to the ten years of ongoing talks at the UN (United Nations), the Austrian ...
via Bing News