INTERNSHIP DETAILS

AI dispatch Intern

CompanyCaterpillar Inc.
LocationWuxi
Work ModeOn Site
PostedMarch 5, 2026
Internship Information
Core Responsibilities
The intern will be responsible for developing core dispatch functions for unmanned mining trucks, focusing on multi-vehicle coordination, task decomposition, vehicle assignment, and path organization under various constraints. A key focus is integrating AI algorithms, such as Reinforcement Learning and Model Predictive Control, to create intelligent dispatch strategies that optimize capacity, reduce waiting times, and enhance safety margins.
Internship Type
part time
Company Size
62178
Visa Sponsorship
No
Language
English
Working Hours
40 hours
Apply Now →

You'll be redirected to
the company's application page

About The Company
For 100 years, we’ve been helping customers build a better, more sustainable world. Our innovative products and services, backed by our global dealer network, provide exceptional value that helps customers succeed. With 2024 sales and revenues of $64.8 billion, Caterpillar Inc. is the world’s leading manufacturer of construction and mining equipment, off-highway diesel and natural gas engines, industrial gas turbines and diesel-electric locomotives. Caterpillar does business on every continent, principally operating through three primary segments – Construction Industries, Resource Industries and Energy & Transportation – and provides financing and related services through our Financial Products segment.
About the Role

Career Area:

Students and Graduates

Job Description:

Your Work Shapes the World at Caterpillar Inc.

When you join Caterpillar, you're joining a global team who cares not just about the work we do – but also about each other.  We are the makers, problem solvers, and future world builders who are creating stronger, more sustainable communities. We don't just talk about progress and innovation here – we make it happen, with our customers, where we work and live. Together, we are building a better world, so we can all enjoy living in it.

矿区无人驾驶调度派遣 Intern(多编组矿卡 / AI 智能调度方向)

岗位职责

调度派遣核心功能开发(多编组)
参与矿区无人矿卡调度系统的核心模块研发,面向多编组(车队/编组/车组)无人矿卡作业,完成包括任务分解、车辆分配、路径/队列组织、装卸点协同、站点排队、交会避让、限速限行等调度派遣能力的实现与优化。 智能化派遣策略与优化算法开发
将新进 AI 算法融入调度派遣:在约束条件(道路等级、坡度、会车规则、站点容量、设备节拍、维护窗口、安全距离、能源/电量等)下,构建智能任务分配与动态重调度策略,实现更高的产能、更低的等待、更少的空驶和更高的安全裕度。 强化学习 / 模型预测 / 图优化在调度中的应用
在仿真或离线数据基础上,探索并实现以下智能决策能力:

  • 基于强化学习(RL的动态派遣策略学习(高扰动场景:拥堵、设备故障、临时封路、装载设备节拍波动等)
  • 基于模型预测控制(MPC/滚动时域优化的多车协同调度
  • 基于图优化/网络流/匹配的车-任务-站点联合优化

前沿技术调研与快速原型
跟进智能调度/运筹优化/多智能体学习最新趋势,将可落地的策略(例如GNNTransformerDiffusion/生成式规划、LLM+工具调用等)用于派遣策略建模、参数自适应、异常诊断与调度解释性输出。

任职要求

学历背景:计算机、自动化、工业工程、运筹优化、交通工程、机器人等相关专业,本科/硕士在读(可长期实习优先),具备扎实的算法与工程能力。 调度/优化基础扎实,图算法:最短路(Dijkstra/A*)、最大流/最小费用流、二分图匹配、车辆路径问题相关,在线调度:滚动优化、动态插单、再优化)。 AI 模型与算法能力:强化学习,图神经网络(GNN),序列建模/Transformer,预测模型 + 决策融合,不确定性建模。 编程与工程能力:熟练使用 PythonPyTorch/TensorFlow 任一)进行模型训练与评估, 具备 C++/Go/Java 任一工程开发能力(至少能读写核心服务代码并做性能优化),熟悉 LinuxGitDocker

Posting Dates:

三月 5, 2026 - 三月 30, 2026

Caterpillar is an Equal Opportunity Employer.  Qualified applicants of any age are encouraged to apply

Not ready to apply? Join our Talent Community.

Key Skills
PythonPyTorchTensorFlowC++GoJavaLinuxGitDockerReinforcement LearningGraph OptimizationModel Predictive ControlShortest Path AlgorithmsMax FlowBipartite MatchingVehicle Routing Problem
Categories
EngineeringSoftwareData & AnalyticsManufacturingLogistics