We study the sampling-based planning problem in Markov decision processes (MDPs) that we can access only through a generative model, usually referred to as Monte-Carlo planning. Our objective is to return a good estimate of the optimal value function at any state while minimizing the number of calls to the generative model, i.e. the sample complexity. We propose a new algorithm, TrailBlazer, able to handle MDPs with a finite or an infinite number of transitions from state-action to next states. TrailBlazer is an adaptive algorithm that exploits possible structures of the MDP by exploring only a subset of states reachable by following near-optimal policies. We provide bounds on its sample complexity that depend on a measure of the quantity of near-optimal states. The algorithm behavior can be considered as an extension of Monte-Carlo sampling (for estimating an expectation) to problems that alternate maximization (over actions) and expectation (over next states). Finally, another appealing feature of TrailBlazer is that it is simple to implement and computationally efficient.

We study the sampling-based planning problem in Markov decision processes (MDPs) that we can access only through a generative model, usually referred to as Monte-Carlo planning. Our objective is to return a good estimate of the optimal value function at any state while minimizing the number of calls to the generative model, i.e. the sample complexity. We propose a new algorithm, TrailBlazer, able to handle MDPs with a finite or an infinite number of transitions from state-action to next states. TrailBlazer is an adaptive algorithm that exploits possible structures of the MDP by exploring only a subset of states reachable by following near-optimal policies. We provide bounds on its sample complexity that depend on a measure of the quantity of near-optimal states. The algorithm behavior can be considered as an extension of Monte-Carlo sampling (for estimating an expectation) to problems that alternate maximization (over actions) and expectation (over next states). Finally, another appealing feature of TrailBlazer is that it is simple to implement and computationally efficient.

Y ou are a robot and you live in a Markov decision process (MDP) with a finite or an infinite number of transitions from state-action to next states. Y ou got brains and so you plan before you act.

Autonomous navigation in off-road environments remains a significant challenge in field robotics, particularly for Unmanned Ground Vehicles (UGVs) tasked with search and rescue, exploration, and surveillance. Effective long-range planning relies on the integration of onboard perception systems with prior environmental knowledge, such as satellite imagery and LiDAR data. This work introduces Trailblazer, a novel framework that automates the conversion of multi-modal sensor data into costmaps, enabling efficient path planning without manual tuning. Unlike traditional approaches, Trailblazer leverages imitation learning and a differentiable A* planner to learn costmaps directly from expert demonstrations, enhancing adaptability across diverse terrains. The proposed methodology was validated through extensive real-world testing, achieving robust performance in dynamic and complex environments, demonstrating Trailblazer's potential for scalable, efficient autonomous navigation.

Simultaneous Localization and Mapping systems are a key enabler for positioning in both handheld and robotic applications. The Hilti SLAM Challenges organized over the past years have been successful at benchmarking some of the world's best SLAM Systems with high accuracy. However, more capabilities of these systems are yet to be explored, such as platform agnosticism across varying sensor suites and multi-session SLAM. These factors indirectly serve as an indicator of robustness and ease of deployment in real-world applications. There exists no dataset plus benchmark combination publicly available, which considers these factors combined. The Hilti SLAM Challenge 2023 Dataset and Benchmark addresses this issue. Additionally, we propose a novel fiducial marker design for a pre-surveyed point on the ground to be observable from an off-the-shelf LiDAR mounted on a robot, and an algorithm to estimate its position at mm-level accuracy. Results from the challenge show an increase in overall participation, single-session SLAM systems getting increasingly accurate, successfully operating across varying sensor suites, but relatively few participants performing multi-session SLAM.

You are a robot and you live in a Markov decision process (MDP) with a finite or an infinite number of transitions from state-action to next states. You got brains and so you plan before you act. Luckily, your roboparents equipped you with a generative model to do some Monte-Carlo planning. The world is waiting for you and you have no time to waste. You want your planning to be efficient.

The breathtaking development of artificial intelligence has dazzled users by composing music, creating images and writing essays, while also raising fears about its implications. Even European Union officials working on groundbreaking rules to govern the emerging technology were caught off guard by AI's rapid rise. The 27-nation bloc proposed the Western world's first AI rules two years ago, focusing on reining in risky but narrowly focused applications. General purpose AI systems like chatbots were barely mentioned. Lawmakers working on the AI Act considered whether to include them but weren't sure how, or even if it was necessary.

Upland helps global businesses accelerate digital transformation with a powerful cloud software library that provides choice, flexibility, and value. Our growing library of products delivers the plug-in processes, reporting, and job specific workflows that major cloud platforms and homegrown systems don't provide. We focus on specific business challenges and support every corner of the organization, operating at scale and delivering quick time to value for our 1,800 enterprise customers. We are experts in knowledge management, trusted by major organizations globally to deliver Connected Knowledge to internal staff and customers. Through years of development and partnerships with leading software vendors, getting the right answers to the right people at the right time, we have created out-of-the-box integrations that can connect multiple repositories alongside the native knowledge base, and display them in the users CRM/ITSM tools or dedicated portals.

Simply mentioning these fields conjures up images inspired by science fiction. Robots that compose music and write novels. Computers that mimic human emotion and predict the future. Yet despite the futuristic visions that these subjects conjure, the reality of AI/ML, on the operations side, has much in common with the past. In the early days of the internet, web developers, the trailblazers of their time, built almost everything from scratch.

SinglePoint, Northern Light's market research and competitive intelligence portal platform, contains three applications of artificial intelligence-based machine learning, all of which enable business professionals to accelerate time-to-insight. First, SinglePoint enables auto-summarization of search results. The search engine reads all of the documents and summarizes the most significant ideas contained in the documents on the search result into an Insights Report. The user can express an interest in knowing more about a topic--what used to be called a "search query"--and then the system delivers a report rather than just a search result. The machine does the search and then tells the user what it finds that the user should know.