This paper introduces SmartBSP, an advanced self-supervised learning framework for real-time path planning and obstacle avoidance in autonomous robotics navigating through complex environments. The proposed system integrates Proximal Policy Optimization (PPO) with Convolutional Neural Networks (CNN) and Actor-Critic architecture to process limited LIDAR inputs and compute spatial decision-making probabilities. The robot's perceptual field is discretized into a grid format, which the CNN analyzes to produce a spatial probability distribution. During the training process a nuanced cost function is minimized that accounts for path curvature, endpoint proximity, and obstacle avoidance. Simulations results in different scenarios validate the algorithm's resilience and adaptability across diverse operational scenarios. Subsequently, Real-time experiments, employing the Robot Operating System (ROS), were carried out to assess the efficacy of the proposed algorithm.

This research introduces an innovative mathematical learning approach that integrates generative AI to cultivate a structured learning rather than quick solution. Our method combines chatbot capabilities and generative AI to offer interactive problem-solving exercises, enhancing learning through a stepby-step approach for varied problems, advocating for the responsible use of AI in education. Our approach emphasizes that immediate answers from ChatGPT can impede real learning. We introduce a reward-based system that requires students to solve mathematical problems effectively to receive the final answer. This encourages a progressive learning path from basic to complex problems, rewarding mastery with final solutions. The goal is to transition students from seeking quick fixes to engaging actively in a comprehensive learning experience.

Autonomous vehicles (AVs) are envisioned to revolutionize our life by providing safe, relaxing, and convenient ground transportation. The computing systems in such vehicles are required to interpret various sensor data and generate responses to the environment in a timely manner to ensure driving safety. However, such timing-related safety requirements are largely unexplored in prior works. In this paper, we conduct a systematic study to understand the timing requirements of AV systems. We focus on investigating and mitigating the sources of tail latency in Level-4 AV computing systems. We observe that the performance of AV algorithms is not uniformly distributed -- instead, the latency is susceptible to vehicle environment fluctuations, such as traffic density. This contributes to burst computation and memory access in response to the traffic, and further leads to tail latency in the system. Furthermore, we observe that tail latency also comes from a mismatch between the pre-configured AV computation pipeline and the dynamic latency requirements in real-world driving scenarios. Based on these observations, we propose a set of system designs to mitigate AV tail latency. We demonstrate our design on widely-used industrial Level-4 AV systems, Baidu Apollo and Autoware. The evaluation shows that our design achieves 1.65 X improvement over the worst-case latency and 1.3 X over the average latency, and avoids 93% of accidents on Apollo.

Open-ended text generation with autoregressive language models (LMs) is one of the core tasks in natural language processing. However, maximization-based decoding methods (e.g., greedy/beam search) often lead to the degeneration problem, i.e., the generated text is unnatural and contains undesirable repetitions. Existing solutions to this problem either introduce randomness prone to incoherence or require a look-ahead mechanism that demands extra computational overhead. In this study, we formulate open-ended text generation from a new perspective, i.e., we view it as an exploration process within a directed graph. Thereby, we understand the phenomenon of degeneration as circular loops within the directed graph. Based on our formulation, we propose a novel decoding method -- \textit{momentum decoding} -- which encourages the LM to \textit{greedily} explore new nodes outside the current graph. Meanwhile, it also allows the LM to return to the existing nodes with a momentum downgraded by a pre-defined resistance function. We extensively test our approach on three benchmarks from different domains through automatic and human evaluations. The results show that momentum decoding performs comparably with the current state of the art while enjoying notably improved inference speed and computation FLOPs. Furthermore, we conduct a detailed analysis to reveal the merits and inner workings of our approach. Our codes and other related resources are publicly available at https://github.com/gmftbyGMFTBY/MomentumDecoding.

We propose a saliency-based, multi-target detection and segmentation framework for multi-aspect, semi-coherent imagery formed from circular-scan, synthetic-aperture sonar (CSAS). Our framework relies on a multi-branch, convolutional encoder-decoder network (MB-CEDN). The encoder portion extracts features from one or more CSAS images of the targets. These features are then split off and fed into multiple decoders that perform pixel-level classification on the extracted features to roughly mask the target in an unsupervised-trained manner and detect foreground and background pixels in a supervised-trained manner. Each of these target-detection estimates provide different perspectives as to what constitute a target. These opinions are cascaded into a deep-parsing network to model contextual and spatial constraints that help isolate targets better than either solution estimate alone. We evaluate our framework using real-world CSAS data with five broad target classes. Since we are the first to consider both CSAS target detection and segmentation, we adapt existing image and video-processing network topologies from the literature for comparative purposes. We show that our framework outperforms supervised deep networks. It greatly outperforms state-of-the-art unsupervised approaches for diverse target and seafloor types.

The silver-and-turquoise lounge, in the Miracle Mile Shops mall on the Strip, has 28 counter-style seats, each equipped with a tablet, facing a bar counter topped with two industrial-grade robotic arms. Patrons can order signature and classic cocktails, or fill a virtual cup with up to 14 ingredients of their choosing. Then the robotic arms go to work, gathering ingredients from a kind of futuristic back-bar automat; reaching up to a lattice of 120 liquor bottles; and tipping the resulting cocktail into a plastic cup proffered by a mechanical dispenser in the counter. Drinks take 60 to 90 seconds to make, and cost $12 to $16, said Stephan Mornet, president of Robotic Innovations, Tipsy Robot's parent company. For its automated bar, Tipsy Robot turned to Makr Shakr, an Italian startup that built its first robot bartender for Google I/O, the annual developer conference, in 2013. The company is one of several trying to automate bartending.

Robots are serving up drinks inside a new bar at the Hard Rock Casino in Mississippi. Jengo, a robot bartender, can make up to 120 drinks an hour. He made his debut during the grand opening on Hard Rock Casino's new "robo bar" on Thursday. Members of the community gathered for the bar's grand opening party. Officials say the venue is only the second of its kind in the country.

Chief executive of Wynn Resorts in Las Vegas enhanced security at his properties after deciding a year ago that Las Vegas was a soft target. This is a rush transcript from "Fox News Sunday," October 8, 2017. This copy may not be in its final form and may be updated. Hurricane Nate hits the Mississippi Gulf Coast. In a week after the Las Vegas massacre, we're still left a simple question: Why? JOE LOMBARDO, LAS VEGAS POLICE SHERIFF: Anything that would indicate this individual trigger points and would cause him to do such harm, we haven't understood that. WALLACE (voice-over): We'll have a live report from Las Vegas with the latest on the investigation. We'll talk with the owner of the town's biggest hotels and casinos, Steve Wynn, who decided a year ago, Las Vegas was a soft target. STEVE WYNN, CHIEF EXECUTIVE, WYNN RESORTS: We profile or inspect or examine everybody that enters the building. And then, even gun rights advocates are calling to revoke bump stock, like the Las Vegas gunman used to make his automatic weapons fire faster. PAUL RYAN, R-WIS., SPEAKER OF THE HOUSE: Fully automatic weapons have been outlawed for many, many years. This seems to be a way of going around that. WALLACE (on camera): Is this the start of sweeping gun control? We'll ask Chris Cox, executive director of the National Rifle Association. Plus, as President Trump decides to decertify the Iran nuclear deal, his, his secretary of state denies he is considered quitting. REX TILLERSON, U.S. SECRETARY OF STATE: The vice president has never had to persuade me to remain the secretary of state because I have never considered leaving this post. DONALD TRUMP, PRESIDENT OF THE UNITED STATES: We must put an end to Iran's continued aggression and nuclear ambitions. WALLACE: We'll ask our Sunday panel about the relationship between the president and Rex Tillerson as they weigh on a major policy change. And our power player of the week, a professional football player goes out of this world to make a difference. UNIDENTIFIED MALE: My perspective shifted, I wanted to come home and really help inspire that next generation. We'll get the latest from the investigation into the Las Vegas mass shooting in a moment with a live report, but we begin with breaking news. Hurricane Nate made landfall early this morning striking Biloxi, Mississippi, with rain and winds of 85 miles per hour, causing flooding and power outages.

Mark Micire makes it very clear: His robot did not rescue any victims of Hurricane Katrina. "We saw inside structures that would not have been able to be searched by a human," said Micire, 29 and president of American Standard Robotics in St. Petersburg. "It's as important to find where not to search as it is where to search." Many buildings were flattened, leaving no more than piles of rubble that rescue workers or dogs could navigate, Micire said. But some damaged buildings hung by a thread, where even a breeze might have caused them to tumble. So risking a robot, despite a $40,000 price tag, is safer than sending rescue personnel into those buildings.

We understand a sociotechnical system as a microsociety in which autonomous parties interact with and about technical objects. We define governance as the administration of such a system by its participants. We develop an approach for governance based on a computational representation of norms. Our approach has the benefit of capturing stakeholder needs precisely while yielding adaptive resource allocation in the face of changes both in stakeholder needs and the environment. We are currently extending this approach to address the problem of secure collaboration and to contribute to the emerging science of cybersecurity.