Collision avoidance algorithms are essential for safe and efficient robot operation among pedestrians. This work proposes using deep reinforcement (RL) learning as a framework to model the complex interactions and cooperation with nearby, decision-making agents (e.g., pedestrians, other robots). Existing RL-based works assume homogeneity of agent policies, use specific motion models over short timescales, or lack a mechanism to consider measurements taken with a large number (possibly varying) of nearby agents. Therefore, this work develops an algorithm that learns collision avoidance among a variety of types of non-communicating, dynamic agents without assuming they follow any particular behavior rules. It extends our previous work by introducing a strategy using Long Short-Term Memory (LSTM) that enables the algorithm to use observations of an arbitrary number of other agents, instead of a small, fixed number of neighbors. The proposed algorithm is shown to outperform a classical collision avoidance algorithm, another deep RL-based algorithm, and scales with the number of agents better (fewer collisions, shorter time to goal) than our previously published learning-based approach. Analysis of the LSTM provides insights into how observations of nearby agents affect the hidden state and quantifies the performance impact of various agent ordering heuristics. The learned policy generalizes to several applications beyond the training scenarios: formation control (arrangement into letters), an implementation on a fleet of four multirotors, and an implementation on a fully autonomous robotic vehicle capable of traveling at human walking speed among pedestrians.

Most common navigation tasks in human environments require auxiliary arm interactions, e.g. opening doors, pressing buttons and pushing obstacles away. This type of navigation tasks, which we call Interactive Navigation, requires the use of mobile manipulators: mobile bases with manipulation capabilities. Interactive Navigation tasks are usually long-horizon and composed of heterogeneous phases of pure navigation, pure manipulation, and their combination. Using the wrong part of the embodiment is inefficient and hinders progress. We propose HRL4IN, a novel Hierarchical RL architecture for Interactive Navigation tasks. HRL4IN exploits the exploration benefits of HRL over flat RL for long-horizon tasks thanks to temporally extended commitments towards subgoals. Different from other HRL solutions, HRL4IN handles the heterogeneous nature of the Interactive Navigation task by creating subgoals in different spaces in different phases of the task. Moreover, HRL4IN selects different parts of the embodiment to use for each phase, improving energy efficiency. We evaluate HRL4IN against flat PPO and HAC, a state-of-the-art HRL algorithm, on Interactive Navigation in two environments - a 2D grid-world environment and a 3D environment with physics simulation. We show that HRL4IN significantly outperforms its baselines in terms of task performance and energy efficiency. More information is available at https://sites.google.com/view/hrl4in.

The global business value derived from Artificial Intelligence (AI) is projected to reach over $3,9 trillion by 2022, according to industry analyst firm Gartner. The firm expects that in the next few years, Artificial Intelligence used to support data science and other algorithm-based applications is going to become the most common use for AI, comprising about 44 percent of the total. To face industry projections, the population needs to prepare by promoting education in AI. Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) is the world's first graduate-level AI university. Named after His Highness Sheikh Mohamed bin Zayed Al Nahyan, Crown Prince of Abu Dhabi and Deputy Supreme Commander of the United Arab Emirates (UAE) Armed Forces, the AI university will introduce a new model of academia and research to the field of Artificial Intelligence.

My hobbies are Reading books, Listening to music, Surfing the internet and Writing articles.

"Using AI 4 HR opened my eyes and created for me a global vision for how artificial intelligence is being used across all areas of HR. I recommended our entire team of HR enroll in this course." "Using AI4HR was a great opportunity to have a first contact with AI in all applications for HR and this gave me a high-level view on the topic. The best part was being able to visualize how to apply AI for HR through real world case studies and seeing what other people and other companies are already doing and the results they were experiencing in their organization. "As a company, we are starting on our journey to deploy artificial intelligence and I found the online course Using AI4HR to be inspirational, practical and a great way to network with other HR leaders on the journey.

Artificial Intelligence (AI) is set to transform our lives from the way we work to the way we live. It has already found its way into many domains and will continue to permeate every aspect of life, society, and work. Microsoft believes every business will rely on AI in five years. If you ask employees, however, they are concerned about job security. In a recent Docebo report, three in five people expressed concerns that AI technology will impact how they perform their job or daily tasks in the future.

At this event we'll explore: Please join the discussions with the leading experts from TLT. The event will be followed by drinks and canapes. For more information please email Philippa McFeat.

There is no bigger industry on our planet than food and agriculture, with a consistent, loyal customer base of 7 billion. In fact, the World Bank estimates that food and agriculture comprise about 10% of the global GDP, meaning that, food and agriculture would be valued at about $8 trillion globally based on the projected global GDP of $88 trillion for 2019. On the food front, a record $1.71 trillion was spent on food and beverages in 2018 at grocery stores and other retailers and away-from-home meals and snacks in the United States alone. During the same year, 9.7% of Americans' disposable personal income was spent on food -- 5% at home and 4.7% away from home -- a percentage that has remained steady amidst economic changes over the past 20 years. However, despite a stalwart customer base, the food industry is facing unprecedented challenges in production, demand and regulations stemming from consumer trends.

A voice-controlled robot that can make you perfect grilled cheese sandwiches on demand has been created by a team of students in the US. 'Cheesborg' is the brainchild of engineer Tayor Tabb, 24, and colleagues, who created the toastie maker at Carnegie Mellon University in Pittsburgh, Pennsylvania. The process begins with a voice command to a connected Google Home smart assistant. The cheesy contraption uses a vacuum to begin to assemble the sandwich -- loading two slices of bread and one slice of cheese onto its conveyor belt. Next, the conveyor moves the ingredients into a sandwich press and closes the lid ready for grilling.

Description: A down-to-earth, shy but confident take on machine learning techniques that you can put to work today.