Mobile robots are increasingly required to navigate and interact within unknown and unstructured environments to meet human demands. Demand-driven navigation (DDN) enables robots to identify and locate objects based on implicit human intent, even when object locations are unknown. However, traditional data-driven DDN methods rely on pre-collected data for model training and decision-making, limiting their generalization capability in unseen scenarios. In this paper, we propose CogDDN, a VLM-based framework that emulates the human cognitive and learning mechanisms by integrating fast and slow thinking systems and selectively identifying key objects essential to fulfilling user demands. CogDDN identifies appropriate target objects by semantically aligning detected objects with the given instructions. Furthermore, it incorporates a dual-process decision-making module, comprising a Heuristic Process for rapid, efficient decisions and an Analytic Process that analyzes past errors, accumulates them in a knowledge base, and continuously improves performance. Chain of Thought (CoT) reasoning strengthens the decision-making process. Extensive closed-loop evaluations on the AI2Thor simulator with the ProcThor dataset show that CogDDN outperforms single-view camera-only methods by 15\%, demonstrating significant improvements in navigation accuracy and adaptability. The project page is available at https://yuehaohuang.github.io/CogDDN/.

AI that analyzes data to help you make decisions is set to be an increasingly big part of business tools, and the systems that do that are getting smarter with a new approach to decision optimization that Microsoft is starting to make available. Machine learning is great at extracting patterns out of large amounts of data but not necessarily good at understanding those patterns, especially in terms of what causes them. A machine learning system might learn that people buy more ice cream in hot weather, but without a common sense understanding of the world, it's just as likely to suggest that if you want the weather to get warmer then you should buy more ice cream. Understanding why things happen helps humans make better decisions, like a doctor picking the best treatment or a business team looking at the results of AB testing to decide which price and packaging will sell more products. There are machine learning systems that deal with causality, but so far this has mostly been restricted to research that focuses on small-scale problems rather than practical, real-world systems because it's been hard to do. Deep learning, which is widely used for machine learning, needs a lot of training data, but humans can gather information and draw conclusions much more efficiently by asking questions, like a doctor asking about your symptoms, a teacher giving students a quiz, a financial advisor understanding whether a low risk or high risk investment is best for you, or a salesperson getting you to talk about what you need from a new car.

I recently had the opportunity to discuss current IBM artificial intelligence developments with Dr. Lisa Amini, an IBM Distinguished Engineer and the Director of IBM Research Cambridge, home to the MIT-IBM Watson AI Lab. Dr. Amini was previously Director of Knowledge & Reasoning Research in the Cognitive Computing group at IBM's TJ Watson Research Center in New York. Dr. Amini earned her Ph.D. degree in Computer Science from Columbia University. Dr. Amini and her team are part of IBM Research tasked with creating the next generation of Automated AI and data science. I was interested in automation's impact on the lifecycles of artificial intelligence and machine learning and centered our discussion around next-generation capabilities for AutoAI. AutoAI automates the highly complex process of finding and optimizing the best ML model, features, and model hyperparameters for your data.

After a few years on Data Science and then Artificial Intelligence, the spotlights are now moving to Trustworthy AI. This post wonders why this new focus, and gives some personal explanations and proposals. AI is applied to many different processes. When you start most recent dish washers, an estimate of the total washing duration is displayed. This is based on AI applied to data coming from dirt and water hardness sensors.

When planning for a day of business, how do you calculate the numerous factors that may affect your bottom-line revenue? For Serco, a company which operates a bike-sharing service throughout London, the answer was in their data. In order to find the most efficient and cost-effective way to manage and maintain 12,000 shared bicycles across 800 stations throughout London, Serco teamed up with IBM Partner DecisionBrain to analyze their customer data and usage patterns. For this project, DecisionBrain used IBM Decision Optimization to calculate the optimal number of bikes needed at each station at any given time, and also to plan efficient routes for maintenance teams to repair and redistribute bikes accordingly. The results were seen in a decrease in company costs and an overall more efficient bike sharing service.

Today, machine learning (ML), artificial intelligence (AI) and decision optimization are not just buzzwords found all over the news. They are urgent requirements for many companies that fear disruption, want to perform pragmatic analysis and make better decisions with their data. Data has been called the next natural resource, like oil. But just as with oil, it must be refined to be valuable, and its end value must exceed the cost of refining it. With data, the value of AI is the cost of investing in collecting, organizing and analyzing all that data.

I just came back from IBM Think 2019 Conference in San Francisco and let me share some thoughts. At IBM Think 2019, I delivered 2 presentations (Optimization in Finance and Machine Learning Optimization) and spent some time meeting customers at our booth at the Event. Now let me go back in time. As a teenager I really enjoyed mathematics and computers. As a hobby I wrote some programs that played Connect 4 and Othello and then later as a student I was lucky to write an Awele program and an early neural networks back in 1995. Even though, I studied aerospace engineering I got really crazy about AI (Artificial Intelligence) and managed to follow a postgraduate degree in AI.

Decision Optimization is now available in the Watson Studio ecosystem with a seamless integration of the CPLEX solvers in the Python runtime environment. Watson Studio now provides everything you need to describe your data, gain insight, and make an optimal decision in the very same ecosystem. Get started right away and learn how to make more intelligent marketing and targeting decisions. Decision Optimization is a subset of data science techniques frequently used for prescriptive analytics. Most documented data science use cases are dedicated to revealing or predicting unknown or future data that is not under your control.

Too often in the past, data science has been a siloed activity that centered around data exploration and insight without truly crossing departmental lines. Those limitations have kept data science from becoming a strategic, enterprise-wide initiative for supporting multiple data science and machine learning projects. Technologies have now matured and become cost-effective enough that an enterprise-class, data science platform can support large scale production requirements. In response, enterprises are directing data science activities across multiple lines of business, using a set of standardized approaches that embrace openness, extensibility, and adaptability. We're now offering Data Science Experience version 1.2, which continues to address all three recommendations above.

In the business world, there are many factors to consider when making the optimal decision. There are so many data points to consider that it becomes a combinatorial problem. For example, consider when and how to raise room rates across a hotel chain based on locations and current events or how best to optimize airline ticket prices given fluctuating fuel costs, factoring in seasonal conditions and local and/or global events. This flows over into our social and personal lives, as we rightly expect to find the nearest coffee shops located to the nearest public libraries or where to buy the cheapest gas closest to the supermarket that stocks the groceries we need. Decision optimization (DO) is the prescriptive element of the data science lifecycle and is key to delivering artificial intelligence, as machine learning (ML) and DO have somewhat of a symbiotic relationship.