اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدReal-time and Large-scale Fleet Allocation of Autonomous Taxis: A Case Study in New York Manhattan Island
66
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Nowadays, autonomous taxis become a highly promising transportation mode, which helps relieve traffic congestion and avoid road accidents. However, it hinders the wide implementation of this service that traditional models fail to efficiently allocate the available fleet to deal with the imbalance of supply (autonomous taxis) and demand (trips), the poor cooperation of taxis, hardly satisfied resource constraints, and on-line platforms requirements. To figure out such urgent problems from a global and more farsighted view, we employ a Constrained Multi-agent Markov Decision Processes (CMMDP) to model fleet allocation decisions, which can be easily split into sub-problems formulated as a Dynamic assignment problem combining both immediate rewards and future gains. We also leverage a Column Generation algorithm to guarantee the efficiency and optimality in a large scale. Through extensive experiments, the proposed approach not only achieves remarkable improvements over the state-of-the-art benchmarks in terms of the individuals efficiency (arriving at 12.40%, 6.54% rise of income and utilization, respectively) and the platforms profit (reaching 4.59% promotion) but also reveals a time-varying fleet adjustment policy to minimize the operation cost of the platform.
قيم البحث
اقرأ أيضاً
In this letter, we propose an integrated autonomous flight and semantic SLAM system that can perform long-range missions and real-time semantic mapping in highly cluttered, unstructured, and GPS-denied under-canopy environments. First, tree trunks an
d ground planes are detected from LIDAR scans. We use a neural network and an instance extraction algorithm to enable semantic segmentation in real time onboard the UAV. Second, detected tree trunk instances are modeled as cylinders and associated across the whole LIDAR sequence. This semantic data association constraints both robot poses as well as trunk landmark models. The output of semantic SLAM is used in state estimation, planning, and control algorithms in real time. The global planner relies on a sparse map to plan the shortest path to the global goal, and the local trajectory planner uses a small but finely discretized robot-centric map to plan a dynamically feasible and collision-free trajectory to the local goal. Both the global path and local trajectory lead to drift-corrected goals, thus helping the UAV execute its mission accurately and safely.
We present LADDER, the first deep reinforcement learning agent that can successfully learn control policies for large-scale real-world problems directly from raw inputs composed of high-level semantic information. The agent is based on an asynchronou
s stochastic variant of DQN (Deep Q Network) named DASQN. The inputs of the agent are plain-text descriptions of states of a game of incomplete information, i.e. real-time large scale online auctions, and the rewards are auction profits of very large scale. We apply the agent to an essential portion of JDs online RTB (real-time bidding) advertising business and find that it easily beats the former state-of-the-art bidding policy that had been carefully engineered and calibrated by human experts: during JD.coms June 18th anniversary sale, the agent increased the companys ads revenue from the portion by more than 50%, while the advertisers ROI (return on investment) also improved significantly.
Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and, thus, are too resource-hungry and computation-intensive
to suit low-capability devices or applications with strict latency requirements. One potential remedy for this is model compression, which has attracted a lot of research attention. Here, we summarize the research in compressing Transformers, focusing on the especially popular BERT model. In particular, we survey the state of the art in compression for BERT, we clarify the current best practices for compressing large-scale Transformer models, and we provide insights into the workings of various methods. Our categorization and analysis also shed light on promising future research directions for achieving lightweight, accurate, and generic NLP models.
Modern Reinforcement Learning (RL) algorithms promise to solve difficult motor control problems directly from raw sensory inputs. Their attraction is due in part to the fact that they can represent a general class of methods that allow to learn a sol
ution with a reasonably set reward and minimal prior knowledge, even in situations where it is difficult or expensive for a human expert. For RL to truly make good on this promise, however, we need algorithms and learning setups that can work across a broad range of problems with minimal problem specific adjustments or engineering. In this paper, we study this idea of generality in the locomotion domain. We develop a learning framework that can learn sophisticated locomotion behavior for a wide spectrum of legged robots, such as bipeds, tripeds, quadrupeds and hexapods, including wheeled variants. Our learning framework relies on a data-efficient, off-policy multi-task RL algorithm and a small set of reward functions that are semantically identical across robots. To underline the general applicability of the method, we keep the hyper-parameter settings and reward definitions constant across experiments and rely exclusively on on-board sensing. For nine different types of robots, including a real-world quadruped robot, we demonstrate that the same algorithm can rapidly learn diverse and reusable locomotion skills without any platform specific adjustments or additional instrumentation of the learning setup.
Roads are a widespread feature of landscapes worldwide, and road traffic sound potentially makes nearby habitat unsuitable for acoustically communicating organisms. It is important to understand the influence of roads at the soundscape level to mitig
ate negative impacts of road sound on individual species as well as subsequent effects on the surrounding landscape. We seek to characterize the relationship between anthropogenic and biological sounds in western New York and assess the extent to which available traffic data explains variability in anthropogenic noise. Recordings were obtained in the spring of 2016 at 18 sites throughout western New York. We used the Welch Power Spectral Density (PSD) at low frequencies (0.5-2 kHz) to represent anthropogenic noise and PSD values at higher frequencies (2-11 kHz) to represent biological sound. Relationships were modeled using a novel two-stage hierarchical Bayesian model utilizing beta regression and basis splines. Model results and map predictions illustrate that anthropogenic noise and biological sound have an inverse relationship, and anthropogenic noise is greatest in close proximity to high traffic volume roads. The predictions have large uncertainty, resulting from the temporal coarseness of public road data used as a proxy for traffic sound. Results suggest that finer temporal resolution traffic sound data, such as crowd-sourced time-indexed traffic data from geographic positioning systems, might better account for observed temporal changes in the soundscape. The use of such data, in combination with the proposed modeling framework, could have important implications for the development of sound management policies.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
