端到端双足导航算法工程师 (VLN方向)
上海
全职
职位描述
1、负责端到端自主导航算法研发,构建面向全尺寸人形机器人的自主导航能力,包括多模态感知、轨迹预测、导航决策等核心模块,持续提升导航智能化水平; 2、负责VLM-Nav/VLN/VLA相关算法研发,构建视觉-语言-动作闭环能力,实现自然语言理解、语义目标定位、路径规划及自主执行; 3、负责多模态感知模型研发,包括RGB、Depth、LiDAR、IMU等多源信息融合,研究BEV、Occupancy、语义地图等环境表征,为导航规划提供统一场景理解能力; 4、负责导航Planner模型研发,探索基于Transformer、Diffusion、World Model等新一代规划算法,实现Waypoint预测、轨迹生成、动态避障及复杂环境下的自主决策; 5、负责双足机器人导航感控融合算法研发,构建导航规划与运动控制协同框架,实现规划轨迹与步态控制、全身控制(WBC)、地形感知等模块的高效协同,提升复杂地形、人群环境及动态场景下的运动稳定性与导航成功率;
职位要求
1、硕士及以上学历,计算机、机器人、人工智能等相关专业; 2、熟悉机器人导航、Embodied AI、VLM/VLA、VLN等相关方向,具有较扎实的算法基础; 3、熟悉以下一个或多个方向: - 端到端自主导航(End-to-End Navigation) - Planner模型(Transformer、Diffusion、World Model等) - 多模态感知(BEV、Occupancy、3D Perception、多传感器融合) - 轨迹预测与运动规划(Trajectory Prediction、Motion Planning) - VLM-Nav / Vision-Language Navigation 4、熟悉深度学习框架(PyTorch等),具备模型训练、调优、部署及性能优化经验; 5、具备较强的问题分析及工程实现能力,能够独立完成算法设计、实验验证、性能分析及线上问题定位; 6、具有良好的团队协作能力,能够推动跨团队合作及复杂系统集成落地。
投递

AGIBOT is an Embodied AI foundation model company developing both the intelligence layer and the corresponding robotic embodiments needed to bring general intelligence into the physical world. Founded in 2023, AGIBOT is building a full-stack Embodied AI platform across foundation models, data infrastructure, simulation, robotic hardware, and deployment. AGIBOT’s “Three Intelligences in One” architecture integrates Locomotion Intelligence, Interaction Intelligence, and Manipulation Intelligence into a unified embodied system. AGIBOT’s portfolio spans humanoid robots, quadrupeds, dexterous systems, and commercial cleaning solutions. In March 2026, AGIBOT announced that its 10,000th robot had rolled off the production line.