Researchers from Alana AI and Heriot-Watt University recently unveiled FurChat, a chatbot that combines generative artificial intelligence and robotics. This AI bot matches surrounding user requests with specific information sources, such as company files. As a result, Furchat can help front desk representatives of airports, businesses, etc.
We have installed chatbots on company websites. So it’s not surprising to see people trying to apply them to real-world environments. However, they must overcome the difficulty of speaking with a robot and the awkwardness of interacting with a screen. However, these developers will eventually overcome these obstacles, so we must prepare for their impacts.
We can only achieve this if we understand how AI robot assistants are improving. This is why we are going to detail what differentiates FurChat from other robots. Later, I will explain how large language models work to further explain this AI bot.
How does this AI robot work?
Experts from Heriot-Watt University and Alana AI combined the Furhat robotic bust and OpenAI’s GPT-3.5 to create FurChat. Researcher Oliver Lemon explained his study on robot AI with Tech Xplore.
“We wanted to study several aspects of embodied AI for natural interaction with humans,” Lemon said. “In particular, we wanted to combine the type of general ‘open domain’ conversation you can have with LLMs like ChatGPT with more useful and specific sources of information. »
“FurChat combines a large language model (LLM) such as ChatGPT or one of the many open source alternatives (e.g. LAMA) with a voice-enabled animated robot,” the researcher added.
“This is the first system we know of that combines LLMs for general conversations and specific information sources (e.g., documents about an organization) with expressive automatic robot animations.”
The FurChat chatbot uses GPT-3.5, the large ChatGPT language model, to generate text responses and facial expressions. Meanwhile, the Furhat AI robot speaks these texts.
The researchers tested the robot by installing it at the UK National Robotarium in Scotland. Visitors interacted with the robot to learn more about the installation and its events.
You may also like: The Ultimate Guide to ChatGPT
Preliminary results show that the FurChat system was effective in communicating with users. He provided the correct information to visitors by communicating smoothly.
The team plans to test similar AI robots in public spaces, festivals, museums and other locations. “We are investigating how to use and further develop recent advances in AI in LLMs to create more useful, usable and compelling systems for collaboration between humans, robots and AI systems in general,” explained Lemon .
“We are working on systems combining vision and language for embodied agents capable of working with humans. This will be of increasing importance in the coming years as more human-AI collaboration systems are developed.
How do AI chatbots work?
It’s hard to understand the importance of creating a human-like AI robot if you don’t know how generative artificial intelligence works. Unlike previous chatbots, it does not rely on predefined responses.
Generative AI robots have large language models, which are databases containing millions of words. These LLMs have algorithms that track embeddings to link user queries to the right words.
You May Also Like: AI Photo Editor Turns Asian Student White
Embeddings measure “text string relatedness”. Additionally, they are very versatile because ChatGPT has multiple use cases. Here are their usual functions:
- Research: Integrations rank queries by relevance.
- Grouping: Embeddings group text strings by similarity.
- Classification: OpenAI integrations classify text strings by their most similar label.
- Anomaly detection: Embeddings identify words with minimal relatedness.
- Recommendations: OpenAI integrations recommend related text strings.
- Measuring diversity: Embeddings analyze how similarities propagate between multiple words.
These systems allow a chatbot to provide answers. Imagine a machine doing this, simulating facial expressions and expressing these responses. This complexity makes FurChat an incredible technological success!
Conclusion
Experts from Alana AI and Heriot-Watt University have created a robot combining generative AI with physical robotic form. As a result, it could “talk” with users as if engaging in a conversation.
Researchers aim to create similar robots for other settings, such as businesses and airports. They also aim to create conversational agents capable of speaking with multiple humans simultaneously.
Learn more about this artificial intelligence research by reading their arXiv journal. Plus, see more digital tips and trends on Inquirer Tech.
Your subscription could not be saved. Try Again.
Your subscription was successful.
Read next
To subscribe to APPLICANT MORE to access The Philippine Daily Inquirer and over 70 other titles, share up to 5 gadgets, listen to news, download as early as 4 a.m. and share articles on social media. Call 896 6000.
For comments, complaints or inquiries, Contact us.
