Artificial intelligence (AI) systems that can play games with humans have become increasingly advanced and have already been deployed by countless videogame developers worldwide. Most of these systems, however, are designed to compete against humans online, on digital platforms and in virtual environments, as opposed to physically in the real-world.

Researchers at Delft University of Technology (TU Delft) recently introduced a new open-source robotic system that can play chess against a human user in a real-world environment. This robot, outlined in a paper pre-published on arXiv, could prove to be a valuable resource for human-robot interaction research.

“Recent advancements in AI have sped up the evolution of versatile robot designs,” Renchi Zhang, Joost de Winter, and their colleagues wrote in their paper. “Chess provides a standardized environment that allows for the evaluation of the influence of robot behaviors on human behavior. This article presents an open-source chess robot for human–robot interaction (HRI) research, specifically focusing on verbal and non-verbal interactions.”

The robotic platform developed by the researchers includes both hardware and software components. The robot’s hardware includes a Franka Emika Panda robotic arm with 7 degrees of freedom, a Franka robotic hand, a customized 3D-printed robotic gripper, a ZED2 StereoLabs camera, a keyboard, an external microphone and speaker connected to a computer, an NVIDIA Jetson Nano computer and a PC.

The robot also has several underlying software components, including a perception, an analysis and evaluation, a motion planning and execution and an interaction module. The perception module analyzes images of the chess board captured by the ZED2 camera and translates them into text descriptions.

Subsequently, the analysis and evaluation module feeds this text descriptions to a chess engine, to derive predicted moves and their corresponding scores. The motion planning and execution module then uses a predicted move to plan and execute the robot’s chess moves.

Finally, the interaction module allows the robot to communicate with the human players they are competing against. To generate responses to a user’s questions, this module relies on the API of OpenAI’s conversational platform ChatGPT.

“OpenChessRobot recognizes chess pieces using computer vision, executes moves, and interacts with the human player using voice and robotic gestures,” the researchers wrote in their paper. “We detail the software design, provide quantitative evaluations of the robot’s efficacy and offer a guide for its reproducibility.”

Zhang, de Winter and their colleagues evaluated their robotic platform in a series of initial tests, assessing its ability to compete against humans at chess. While they have not yet explored the perception of users who interacted with the robot, they found that the robot could effectively plan its future chess moves and move pieces to the desired locations on the board.

The robot’s underlying code and the datasets used to train its classifiers are open-source and can be accessed on GitHub. The robot could thus soon be fabricated at other institutes to carry out further studies focusing on human-robot interaction.

“In the future, we intend to leverage this setup to study how AI-embodied robots influence people during interactions,” Zhang, de Winter and their colleagues wrote. “This will involve the robot communicating with humans through emotional expressions and more natural verbal interactions. Extending the OpenChessRobot’s capabilities beyond the chess application to general physical assistance is also an intriguing avenue to explore.”

© 2024 Science X Network

Carole Will McDonald didn’t think she would find a blue-eyed cicada when she went looking for one in her front yard in Niles. It was a one-in-a-million shot, she understood, to find one amidst its red-eyed brethren in a sea of cicadas that have taken over the northern suburbs with their signature singing and clumsy flying.

“It was pretty cool… I mean, he did stand out from the others,” McDonald recalled thinking when she first saw it. After taking a picture of the statistical anomaly, she shared what she saw on social media and reached out to the Field Museum to see if they were interested in the sighting.

According to Paul Gulezian, distinguished professor of biology at Oakton College, finding a blue-eyed cicada is indeed a rare occasion. He said that the sightings are known colloquially as one-in-a-million, but studies have also found that cicadas with blue eyes are one in a quarter million.

Gulezian added that there are likely hundreds of millions to one billion cicadas in northern Illinois. A fair estimate of how many of them have blue eyes could be between 1,000 to 10,000, he said. “The vast majority of them go undetected by people, or maybe a bird or a squirrel gets to them… But it is amazing that we’ve actually documented a couple of them, given how rare they are.”

Blue-eyed cicadas have also been spotted in the Southwest suburbs. Gulezian said that there are a couple of leading theories why some cicadas have blue eyes. He said a blue-eyed cicada might have a different DNA strand that gives it blue eyes. Another theory is that when cicadas shed their skin, a thin layer of their exoskeleton might hang on their eyes, given the appearance that their eyes might be blue.

2024 Chicago Tribune. Distributed by Tribune Content Agency, LLC.

Connectivity has become paramount in modern societies over the past two decades. With the immense rise in the number of laptops, tablets, and smartphones, most people nowadays expect to have access to free Wi-Fi in a variety of public and private spaces. Some common examples include airports, restaurants, and libraries, but even parks, trains, and subways offer Wi-Fi in some cities.

However, most wireless environments are based on the IEEE802.11 WLAN standards. Though undoubtedly an amazing feat of engineering, these standards suffer from inherent problems that can lower their performance for all users in a network.

For example, if a slow user joins a wireless local-area network (WLAN), their slow transmission rate can affect the throughput rate of other users, since users share the communication channels of the access point (AP, or “router”) by taking turns using it. Moreover, users can also interfere with each other when attempting to communicate with the AP, negatively impacting each other’s performance.

Scientists have come up with a few strategies to try to minimize the effects of these problems and improve the overall throughput of APs. Some of these methods are cooperative, meaning that users can be prompted by the AP to change their position in order to improve system throughput.

Though this is indeed a promising strategy, many existing techniques fail to simultaneously consider the interference between users and each user’s transmission rate. In turn, other techniques fail to account for the possibility that some users may be fixed, whereas others can move.

To address these limitations, a research team including Associate Professor Sumiko Miyata from Shibaura Institute of Technology (SIT) has developed a novel AP connection method using game theory. Their latest paper, which was authored by Yu Kato from SIT and co-authored by Jiquan Xie and Tutomu Murase from Nagoya University, is published in the IEEE Open Journal of the Communications Society.

Game theory is a branch of mathematics that mainly deals with the analysis of decisions and decision-making, especially within clearly defined frameworks (“games”) with rules, possible actions, and agents. Usually, the goal in game theory analysis is to identify optimal strategies.

“For wireless communication environments where multiple users exist and must be considered, game theory is one of the most suitable theories to use for analysis,” explains Dr. Miyata. “In the approach proposed in our paper, the user position that maximizes system throughput is determined using what’s known as a ‘potential game,’ which is a type of model in game theory.”

The developed potential game model, whose objective function is to maximize system throughput, condenses the incentives for all users into a single function. In this way, and unlike previous methods, the impact of the position of new users joining a WLAN on existing users is considered. Moreover, the new approach also takes into account inter-user interference by calculating the probabilities of packet collisions.

The researchers tested their proposed AP connection strategy, which was directly based on their potential game model, by comparing it with previous AP connection methods. They analyzed the resulting AP throughput for each method in a wide variety of scenarios involving different user positions. In this way, they proved that their proposed strategy almost always resulted in a throughput improvement compared to other techniques, with the improvement in system performance reaching up to 6% in some cases.

Although having a router prompt existing or new users to move around is not feasible in every situation, the proposed strategy could find a home in certain environments.

“Our method could be a potential option for Wi-Fi services in classrooms and libraries due to their location-free characteristics and low human traffic,” explains Dr. Miyata. “The Wi-Fi system would calculate the optimal user positions based on their locations to enhance overall throughput and encourage them to take cooperative action, motivated by a desire to increase their own throughput as well.”

Overall, methods like the one developed in this study are significant, given the innumerable number of Wi-Fi-enabled devices present today.

“AP systems should be efficient regarding the use of their network resources. The proposed technique is an important technology for realizing smart cities, where everything is connected to the internet,” concludes Dr. Miyata