This article presents five programming problems from Hulu's 2022 campus recruitment—including particle simulation, Sophie‑N number counting, optimal activity point on a tree, devil‑maze navigation, and non‑intersecting triangles—complete with problem statements, input/output specifications, sample cases, and detailed solution approaches.
In the Tencent Geek Challenge, Wang Haosheng leveraged a custom Tetris simulator and intensive hand‑play—enhanced with limited AI tools—to clear all 10,000 blocks, achieving 1.179 million points and third place, illustrating that manual strategy outperformed the AI despite extensive competition and technical analysis.
This article reviews the selection of a 2D physics engine for mechanics experiments, compares Box2D and Nape, details eight test scenarios highlighting precision, constraint, mass‑density, friction, and buoyancy problems, and proposes practical solutions to improve simulation accuracy and usability.
DiDi’s autonomous‑driving simulation suite combines a high‑fidelity vehicle‑environment simulator, a massively parallel cloud platform, and a robust data management system—leveraging neural‑net caching, mixed‑deployment resources, and virtual‑clock techniques—to replay historic drives, generate extreme virtual scenarios, and efficiently evaluate Level‑4+ algorithms at scale.
The Intelligent UAV Path Planning Simulation System leverages open‑source SITL and FlightGear to model dynamics, visualize 2D/3D environments, and generate exportable flight routes that enable coordinated multi‑drone missions with high precision, addressing traditional UAV planning limitations.
This article outlines a comprehensive framework for designing decision‑type products, covering their evolution stages, core elements of model‑data‑strategy, domain modeling techniques, data‑to‑knowledge transformation, business and process value, and a feedback‑driven decision loop with evaluation and simulation.
This article explains what decision‑type products are, outlines their evolution stages, and details the essential design roadmap—including domain modeling, data value extraction, process standardization, system integration, and building a sustainable decision‑feedback loop—to help product teams create automated, data‑driven solutions that continuously improve business outcomes.
This article explains a promotional bottle‑exchange problem, presents example inputs and outputs, and demonstrates two greedy‑algorithm implementations in Java that compute the maximum number of bottles one can drink when empty bottles can be exchanged for new ones.
This article details the design, implementation, and performance testing of a Go‑based backend that simulates a Spring Festival red‑packet system capable of handling up to 6 × 10⁴ QPS and one million concurrent connections, demonstrating how to achieve 10 billion request processing in a controlled environment.
This article presents a comprehensive technical overview of urban aerial highways for low‑altitude UAV traffic, covering the background, spatiotemporal big‑data foundations, safety‑radius modeling, risk assessment, network and drone models, centralized and distributed control algorithms, simulation platforms, experimental results, and future research directions.
NetEase Yanxuan built a cloud‑native supply‑chain simulation platform that standardizes data flows, achieves 97% forecasting accuracy, processes billions of orders daily, and reduces decision cycles, enabling over thirty major business choices with cost savings of tens of millions.
DARPA’s ACE program showcased the AI‑driven fighter Falco, built with the open‑source AdeptRL reinforcement‑learning framework, which defeated an experienced US Air Force instructor in a 1‑v‑1 simulated F‑16 dogfight, highlighting both the promise and current limitations of autonomous combat systems.
This article explains how to overcome the limitations of PC‑based simulators for in‑vehicle navigation development by using a Thrift‑based proxy (Sandwich) to forward car‑side signals to a PC, enable bidirectional debugging, and project map rendering back to the vehicle display.
SuNing’s AI R&D Center and Logistics Institute created a digital twin platform that maps physical warehouse systems to virtual models, automatically generates simulation scenarios, optimizes strategies, and feeds results back to improve overall storage operations, achieving over 15% efficiency gains.
Simulation enables low‑cost, time‑agnostic testing of e‑commerce supply‑chain strategies—covering procurement, inter‑warehouse allocation, and order dispatch—by combining precedent, experimentation, and modeling, offering a more flexible and comprehensive alternative to AB‑testing for evaluating policies, algorithms, and configurations.
This tutorial demonstrates how to build a vivid fireworks simulation in Python using Pygame, covering module imports, window setup, color configuration, a Fireworks class definition, particle dynamics, and the main game loop for rendering and animation.
By extracting hour‑level activity logs and training supervised models—including CART, GBDT, and neural networks—on user tags, the team simulated short‑term metrics for new reward campaigns, enabling earlier prediction of next‑day retention and shortening experiment cycles despite delayed T+1 data.
This article outlines Pony.ai's comprehensive autonomous driving infrastructure, describing traditional internet back‑end components, additional vehicle‑mounted systems, large‑scale simulation, data challenges, and the reliability, performance, and flexibility practices needed to support rapid growth and safe robotaxi operations.
The article traces the evolution of autonomous driving from early concepts to modern implementations, highlighting Pony.ai’s technical innovations in sensor fusion, high‑definition mapping, simulation, data processing, software iteration, and the challenges of scaling vehicle fleets for commercial deployment.
The article presents a comprehensive overview of Pony.ai's autonomous driving infrastructure, covering the core infrastructure team’s responsibilities, vehicle onboard systems, simulation platform, data architecture, and supporting services, while discussing the technical challenges and engineering practices employed to achieve scalability, reliability, and high performance.
A Python Monte‑Carlo simulation of a daily dice‑betting game shows that even with a 50% win rate per round, 83% of gamblers go bankrupt within eight years, highlighting the randomness of gambling profits and the near‑zero chance of beating the casino.
The article explains Alibaba’s Sigma container‑scheduling system and its Cerebro simulation platform, detailing how they improve resource utilization, reduce costs during large‑scale events like Double‑11, and address challenges such as fragmentation, rapid scaling, image distribution, and accurate workload forecasting.
Meituan’s AI‑driven “super brain” dispatch system combines big‑data‑fueled preparation‑time predictions, operations‑research optimization and reinforcement‑learning‑based routing to solve a dynamic vehicle‑routing problem in seconds, cutting average delivery time from 41 to 28 minutes, lowering per‑order cost over 20 % and reducing power use by 19 %.
A Python simulation of 1,000 gamblers playing daily dice bets shows an 83.3% bankruptcy rate, with half going broke within a year, revealing why even a 50% win chance leads most players to ruin despite occasional high earners.
This article demystifies the common myth that programming requires advanced mathematics, outlining the essential arithmetic, number‑system concepts, and occasional higher‑level topics like geometry, physics, and cryptography, while showing how simple simulations can reveal the impact of small statistical changes.
The author recounts attending a Phoenix Project‑based DevOps simulation in Beijing, describing role misunderstandings, the use of Kanban boards, bottleneck handling, one‑piece flow, and communication challenges, and concludes with recommendations on who should participate in such training.
This article explains the key storage I/O characteristics—such as I/O size, read/write ratio, random versus sequential access, and workload patterns—across typical application types, providing reference values and guidance for storage simulation and performance testing using tools like Iometer.
After attending the Phoenix Project DevOps simulation in Beijing, I reflect on five key lessons—understanding role responsibilities, leveraging visual tools, focusing on value‑driven goals, applying one‑piece flow, and reducing hand‑offs—to improve operational efficiency and foster a DevOps mindset.
This article introduces the Monte Carlo method and demonstrates its versatility through five examples covering π estimation, integral calculation, traffic‑jam simulation, product thickness reliability, and securities market profit forecasting, highlighting its simplicity, power, and broad applicability.
