Automated vehicles require a comprehensive understanding of traffic situations to ensure safe and anticipatory driving. In this context, the prediction of pedestrians is particularly challenging as pedestrian behavior can be influenced by multiple factors. In this paper, we thoroughly analyze the requirements on pedestrian behavior prediction for automated driving via a system-level approach. To this end we investigate real-world pedestrian-vehicle interactions with human drivers. Based on human driving behavior we then derive appropriate reaction patterns of an automated vehicle and determine requirements for the prediction of pedestrians. This includes a novel metric tailored to measure prediction performance from a system-level perspective. The proposed metric is evaluated on a large-scale dataset comprising thousands of real-world pedestrian-vehicle interactions. We furthermore conduct an ablation study to evaluate the importance of different contextual cues and compare these results to ones obtained using established performance metrics for pedestrian prediction. Our results highlight the importance of a system-level approach to pedestrian behavior prediction.

"Okay, Google, what's the weather today?" "Sorry, I don't understand." Does the experience--interacting with smart machines that don't respond to orders--sound familiar? This failure may leave people feeling dumbfounded, as if their intelligence were not on the same wavelength as the machines'. While this is not the intention of AI development (to interact selectively), such incidents are likely more frequent for "minorities" in the tech world. The global artificial intelligence (AI) software market is forecast to boom in the coming years, reaching around 126 billion US dollars by 2025.

The nifty app CamFind has come a long way with its artificial intelligence. It uses image recognition to identify an object when you point your smartphone camera at it. But back in 2015 its algorithms were less advanced: The app mostly used contract workers in the Philippines to quickly type what they saw through a user's phone camera, CamFind's co-founder confirmed to me recently. You would not have guessed that from a press release it put out that year which touted industry-leading "deep learning technology," but did not mention any human labellers. The practice of hiding human input in AI systems still remains an open secret among those who work in machine learning and AI.

The upcoming video game "Call of Duty: Vanguard" transports you back to World War II – but the latest entrant in the multibillion-selling franchises promises different perspectives of the global conflict. That diversity of perspectives is what you see deployed front and center in the main characters in the game, due out Nov. 5 for PlayStation 5, PS4, Xbox Series X/S, Xbox One, and PCs. Arthur Kingsley, who is Black and Russian sniper Lt. Polina Petrova, alongside squad mates Brooklyn-born pilot Wade Jackson, identified as a first-generation American, Australian explosives expert Lucas Riggs, and second-in-command Sgt. Richard Webb, who is white. This team – a precursor to the modern Special Forces units – is assembled for a mission to enter Berlin and thwart a German plan to establish a Fourth Reich.

Anticipatory expression underlies human performance. Medical conditions and, especially, aging result in diminished anticipatory action. In order to mitigate the loss, means for engaging still available resources (capabilities) can be provided. In particular, anticipation-driven adaptive environments could be beneficial in medical care, as well as in assisted living for those seeking such assistance. These adaptive environments are conceived to be individualized and individualizable, in order to stimulate independent action instead of creating dependencies.

Genetic Programming (GP), an evolutionary learning technique, has multiple applications in machine learning such as curve fitting, data modelling, feature selection, classification etc. GP has several inherent parallel steps, making it an ideal candidate for GPU based parallelization. This paper describes a GPU accelerated stack-based variant of the generational GP algorithm which can be used for symbolic regression and binary classification. The selection and evaluation steps of the generational GP algorithm are parallelized using CUDA. We introduce representing candidate solution expressions as prefix lists, which enables evaluation using a fixed-length stack in GPU memory. CUDA based matrix vector operations are also used for computation of the fitness of population programs. We evaluate our algorithm on synthetic datasets for the Pagie Polynomial (ranging in size from $4096$ to $16$ million points), profiling training times of our algorithm with other standard symbolic regression libraries viz. gplearn, TensorGP and KarooGP. In addition, using $6$ large-scale regression and classification datasets usually used for comparing gradient boosting algorithms, we run performance benchmarks on our algorithm and gplearn, profiling the training time, test accuracy, and loss. On an NVIDIA DGX-A100 GPU, our algorithm outperforms all the previously listed frameworks, and in particular, achieves average speedups of $119\times$ and $40\times$ against gplearn on the synthetic and large scale datasets respectively.

Existing studies on semantic parsing focus primarily on mapping a natural-language utterance to a corresponding logical form in one turn. However, because natural language can contain a great deal of ambiguity and variability, this is a difficult challenge. In this work, we investigate an interactive semantic parsing framework that explains the predicted logical form step by step in natural language and enables the user to make corrections through natural-language feedback for individual steps. We focus on question answering over knowledge bases (KBQA) as an instantiation of our framework, aiming to increase the transparency of the parsing process and help the user appropriately trust the final answer. To do so, we construct INSPIRED, a crowdsourced dialogue dataset derived from the ComplexWebQuestions dataset. Our experiments show that the interactive framework with human feedback has the potential to greatly improve overall parse accuracy. Furthermore, we develop a pipeline for dialogue simulation to evaluate our framework w.r.t. a variety of state-of-the-art KBQA models without involving further crowdsourcing effort. The results demonstrate that our interactive semantic parsing framework promises to be effective across such models.

For the last two years, Facebook AI Research (FAIR) has worked with 13 universities around the world to assemble the largest ever data set of first-person video--specifically to train deep-learning image-recognition models. AIs trained on the data set will be better at controlling robots that interact with people, or interpreting images from smart glasses. "Machines will be able to help us in our daily lives only if they really understand the world through our eyes," says Kristen Grauman at FAIR, who leads the project. Such tech could support people who need assistance around the home, or guide people in tasks they are learning to complete. "The video in this data set is much closer to how humans observe the world," says Michael Ryoo, a computer vision researcher at Google Brain and Stony Brook University in New York, who is not involved in Ego4D.

The US military may be getting a dog-like quadruped robot armed with a sniper rifle. The robot, developed by Ghost Robotics of Philadelphia, is a new version of its Vision series of legged robots. The US Air Force is currently testing an unarmed version of these robots for use as perimeter security at the Tyndall Air Force Base in Florida. Ghost Robotics displayed the armed version at the annual meeting of the Association of the United States Army held in Washington DC this week. The robot is fitted with a Special Purpose Unmanned Rifle pod from Sword Defense, with a powerful 6.5mm sniper rifle.

Researchers at Carnegie Mellon University helped compile and will have access to the largest collection of point-of-view videos in the world. These videos could enable artificial intelligence to understand the world from a first-person point of view and unlock a new wave of virtual assistants, augmented reality and robotics. Until now, most of the video used to train computer vision models came from the third-person point of view. The first-person, or egocentric, video included in this collection will allow researchers to train computer vision systems to see the world as humans do. "For the first time, we'll have enough data to be able to teach computers to see what we see," said Kris Kitani, an associate research professor in the Robotics Institute who led CMU's efforts to collect data.