The growth of autonomous vehicles, ridesharing systems, and self driving technology will bring a shift in the way ride hailing platforms plan out their services. However, these advances in technology coupled with road congestion, environmental concerns, fuel usage, vehicles emissions, and the high cost of the vehicle usage have brought more attention to better utilize the use of vehicles and their capacities. In this paper, we propose a novel multi-hop ride-sharing (MHRS) algorithm that uses deep reinforcement learning to learn optimal vehicle dispatch and matching decisions by interacting with the external environment. By allowing customers to transfer between vehicles, i.e., ride with one vehicle for sometime and then transfer to another one, MHRS helps in attaining 30\% lower cost and 20\% more efficient utilization of fleets, as compared to the ride-sharing algorithms. This flexibility of multi-hop feature gives a seamless experience to customers and ride-sharing companies, and thus improves ride-sharing services.

Path planning is a fundamental and extensively explored problem in robotic control. We present a novel economic perspective on path planning. Specifically, we investigate strategic interactions among path planning agents using a game theoretic path planning framework. Our focus is on economic tension between two important objectives: efficiency in the agents' achieving their goals, and safety in navigating towards these. We begin by developing a novel mathematical formulation for path planning that trades off these objectives, when behavior of other agents is fixed. We then use this formulation for approximating Nash equilibria in path planning games, as well as to develop a multi-agent cooperative path planning formulation. Through several case studies, we show that in a path planning game, safety is often significantly compromised compared to a cooperative solution.

In Interactive Machine Learning (IML), we iteratively make decisions and obtain noisy observations of an unknown function. While IML methods, e.g., Bayesian optimization and active learning, have been successful in applications, on real-world systems they must provably avoid unsafe decisions. To this end, safe IML algorithms must carefully learn about a priori unknown constraints without making unsafe decisions. Existing algorithms for this problem learn about the safety of all decisions to ensure convergence. This is sample-inefficient, as it explores decisions that are not relevant for the original IML objective. In this paper, we introduce a novel framework that renders any existing unsafe IML algorithm safe. Our method works as an add-on that takes suggested decisions as input and exploits regularity assumptions in terms of a Gaussian process prior in order to efficiently learn about their safety. As a result, we only explore the safe set when necessary for the IML problem. We apply our framework to safe Bayesian optimization and to safe exploration in deterministic Markov Decision Processes (MDP), which have been analyzed separately before. Our method outperforms other algorithms empirically.

--Semantic understanding of scenes in three-dimensional space (3D) is a quintessential part of robotics oriented applications such as autonomous driving as it provides geometric cues such as size, orientation and true distance of separation to objects which are crucial for taking mission critical decisions. As a first step, in this work we investigate the possibility of semantically classifying different parts of a given scene in 3D by learning the underlying geometric context in addition to the texture cues BUT in the absence of labelled real-world datasets. T o this end we generate a large number of synthetic scenes, their pixel-wise labels and corresponding 3D representations using CARLA software framework. We then build a deep neural network that learns underlying category specific 3D representation and texture cues from color information of the rendered synthetic scenes. Further on we apply the learned model on different real world datasets to evaluate its performance. Our preliminary investigation of results show that the neural network is able to learn the geometric context from synthetic scenes and effectively apply this knowledge to classify each point of a 3D representation of a scene in real-world.

We propose a contrastive attention mechanism to extend the sequence-to-sequence framework for abstractive sentence summarization task, which aims to generate a brief summary of a given source sentence. The proposed contrastive attention mechanism accommodates two categories of attention: one is the conventional attention that attends to relevant parts of the source sentence, the other is the opponent attention that attends to irrelevant or less relevant parts of the source sentence. Both attentions are trained in an opposite way so that the contribution from the conventional attention is encouraged and the contribution from the opponent attention is discouraged through a novel softmax and softmin functionality. Experiments on benchmark datasets show that, the proposed contrastive attention mechanism is more focused on the relevant parts for the summary than the conventional attention mechanism, and greatly advances the state-of-the-art performance on the abstractive sentence summarization task. We release the code at https://github.com/travel-go/

A deep neural network (DNN) classifier represents a model owner's intellectual property as training a DNN classifier often requires lots of resource. Watermarking was recently proposed to protect the intellectual property of DNN classifiers. However, watermarking suffers from a key limitation: it sacrifices the utility/accuracy of the model owner's classifier because it tampers the classifier's training or fine-tuning process. In this work, we propose IPGuard, the first method to protect intellectual property of DNN classifiers that provably incurs no accuracy loss for the classifiers. Our key observation is that a DNN classifier can be uniquely represented by its classification boundary. Based on this observation, IPGuard extracts some data points near the classification boundary of the model owner's classifier and uses them to fingerprint the classifier. A DNN classifier is said to be a pirated version of the model owner's classifier if they predict the same labels for most fingerprinting data points. IPGuard is qualitatively different from watermarking. Specifically, IPGuard extracts fingerprinting data points near the classification boundary of a classifier that is already trained, while watermarking embeds watermarks into a classifier during its training or fine-tuning process. We extensively evaluate IPGuard on CIFAR-10, CIFAR-100, and ImageNet datasets. Our results show that IPGuard can robustly identify post-processed versions of the model owner's classifier as pirated versions of the classifier, and IPGuard can identify classifiers, which are not the model owner's classifier nor its post-processed versions, as non-pirated versions of the classifier.

It's not often that someone wants to see your poop, particularly connected to MIT, but here we are. Microbial health company Seed asks netizens to #giveashit and contibute to what's essentially the world's first poop database (at least officially). By uploading pictures of your feces, you can help scientists train an out-of-MIT health AI called auggi and, hopefully, 1 in 5 people in the US who suffer from chronic gut conditions like IBS. "We don't always think about stool as like a daily data -- I'm putting air quotes around "dump" -- but really, as a direct output of our gut health," said Ara Katz, the co-founder and co-CEO of Seed Health, in a The Verge report. To #GIVEaSHIT, like the company asks, it won't be enough to submit any old photo of your stool. You'll have to visit seed.com/poop,

It is only natural that businesses look within their own territory or market to learn about new technology. But chatbots are a global phenomenon, adopted far faster outside the west that most others, so taking a look at their growth, use and adoption globally provides some valuable insights. Both countries have populations of over 1.3 billion people, or over a third of the world's population. That makes them the global focus for customer service automation to battle the sheer volume of calls that even a small public business will receive. Banks, airlines and hotels are adopting chatbots at high speed to cope with the demand, with the likes of WeChat dominating platform usage with its 700 million users across Asia.

Every parent worries about the influences our children are exposed to. What movies are they watching? What video games are they playing? Are they hanging out with the right crowd? We scrutinize these influences because we know they can affect, for better or worse, the decisions our children make.

State-of-the-art machine learning algorithms can extract two-dimensional objects from photographs and render them faithfully in three dimensions. It's a technique that's applicable to augmented reality apps and robotics as well as navigation, which is why it's an acute area of research for Facebook. In a blog post today ahead of the International Conference on Computer Vision (ICCV) in Seoul, Facebook highlighted its latest advancements with respect to intelligent content-understanding. It says that together, its systems can be used to detect even complex foreground and background objects, like the legs of a chair or overlapping furniture. "[Our] research builds on recent advances in using deep learning to predict and localize objects in an image, as well as new tools and architectures for 3D shape understanding, like voxels, point clouds, and meshes," wrote Facebook researchers Georgia Gkioxari, Shubham Tulsiani, and David Novotny in a blog post.