Natural Language Processing
Assembly Line
Towards Helpful Robots: Grounding Language in Robotic Affordances
In “Do As I Can, Not As I Say: Grounding Language in Robotic Affordances”, we present a novel approach, developed in partnership with Everyday Robots, that leverages advanced language model knowledge to enable a physical agent, such as a robot, to follow high-level textual instructions for physically-grounded tasks, while grounding the language model in tasks that are feasible within a specific real-world context. We evaluate our method, which we call PaLM-SayCan, by placing robots in a real kitchen setting and giving them tasks expressed in natural language. We observe highly interpretable results for temporally-extended complex and abstract tasks, like “I just worked out, please bring me a snack and a drink to recover.” Specifically, we demonstrate that grounding the language model in the real world nearly halves errors over non-grounded baselines. We are also excited to release a robot simulation setup where the research community can test this approach.
Mitsubishi Electric Develops Teaching-less Robot System Technology
Mitsubishi Electric Corporation announced it has developed a teaching-less robot system technology to enable robots to perform tasks, such as sorting and arrangement as fast as humans without having to be taught by specialists. The system incorporates Mitsubishi Electric’s Maisart AI technologies including high-precision speech recognition, which allows operators to issue voice instructions to initiate work tasks and then fine-tune robot movements as required. The technology is expected to be applied in facilities such as food-processing factories where items change frequently, which has made it difficult until now to introduce robots. Mitsubishi Electric aims to commercialize the technology in or after 2023 following further performance enhancements and extensive verifications.
Can Robots Follow Instructions for New Tasks?
The results of this research show that simple imitation learning approaches can be scaled in a way that enables zero-shot generalization to new tasks. That is, it shows one of the first indications of robots being able to successfully carry out behaviors that were not in the training data. Interestingly, language embeddings pre-trained on ungrounded language corpora make for excellent task conditioners. We demonstrated that natural language models can not only provide a flexible input interface to robots, but that pretrained language representations actually confer new generalization capabilities to the downstream policy, such as composing unseen object pairs together.
In the course of building this system, we confirmed that periodic human interventions are a simple but important technique for achieving good performance. While there is a substantial amount of work to be done in the future, we believe that the zero-shot generalization capabilities of BC-Z are an important advancement towards increasing the generality of robotic learning systems and allowing people to command robots. We have released the teleoperated demonstrations used to train the policy in this paper, which we hope will provide researchers with a valuable resource for future multi-task robotic learning research.
Adopting neural language models for the telecom domain
In recent years, transformer-based language models have become the go-to approach in NLP. The transformer model itself is not restricted to the NLP domain, although that is where the architecture has found its greatest use. Similar to recurrent neural network (RNN)-based architectures, the transformer is designed to deal with sequential data. Unlike RNN-based models, however, transformers do not need to process sequential data in order. This is due to non-recurrent attention mechanisms, which replace sequential processing with matrix multiplications and therefore have the benefit of inherent parallelization and greatly reduced training times.
The potential use cases for language models within the telecom industry will grow in number if the models possess knowledge about the domain. To this end, our new benchmark, TeleQuAD, makes it possible to both adapt and evaluate models for the question answering task within the telecom domain. In future work, such benchmarks could also be developed for other downstream tasks, such as entity recognition, log-analysis, classification, and summarization. Furthermore, a telecom language model could be applied to tasks as diverse as software development and infrastructure configuration, for example, code generation, debugging, and automated documentation.
Appliance Maker Implements Speech Recognition Software on the Assembly Line
For BSH, Fluent.ai created a voice-recognition system that lets heavy machine operators at each workstation speak a Wakeword followed by a command into a headset. The word and command trigger the appropriate movement of an appliance on the assembly line. Previously, an operator pressed a button at his workstation to move an appliance along the line to the next station. This movement took up to four seconds between work areas.
Because the AI-based technology is hands-free, Hauer says that workers experience less fatigue and are much more productive. He points out that early results show worker efficiency has increased an average of 75 to 100 percent. “Implementing [this] technology has cut the [appliance transference] time from four seconds to one and a half,” says Markus Maier, project lead at Traunreut. “In the long run, the production time savings will be invaluable. We started [using the voice-recognition system] on one factory assembly line, then [increased it to] three, and [are now] considering rolling out the technology worldwide.”
The history of Amazon’s forecasting algorithm
Historical patterns can be leveraged to make decisions on inventory levels for products with predictable consumption patterns — think household staples like laundry detergent or trash bags. However, most products exhibit a variability in demand due to factors that are beyond Amazon’s control.
Today, Amazon’s forecasting team has drawn on advances in fields like deep learning, image recognition and natural language processing to develop a forecasting model that makes accurate decisions across diverse product categories. Arriving at this unified forecasting model hasn’t been the result of one “eureka” moment. Rather, it has been a decade-plus long journey.
AI project to 'pandemic-proof' NHS supply chain
With the ability to analyse NHS and global procurement data from previous supply contracts, the platform will aim to allow NHS buyers to evaluate credibility and capability of suppliers to fulfil their order. Each supplier would have a real-time ‘risk rating’ with information on the goods and services they supply.
Researchers at Sheffield University’s Information School are said to be developing Natural Language Processing (NLP) methods for the automated reading and extraction of data from large amounts of contract tender data held by the NHS and other European healthcare providers
Knowledge base construction to improve voice-enabled AI in industrial settings
In this research, we focus on building a framework for constructing a KB of equipment components and their problems entities with “component