Research Intern: Bird's Eye View Perception - Honda Research Institute USA

Research Intern: Bird's Eye View Perception

Your application is being processed

Research Intern: Bird's Eye View Perception

Job Number: P25INT-44
Honda Research Institute USA (HRI-US) is seeking a highly motivated intern to develop Bird's-Eye-View (BEV) perception algorithms for semantic reconstruction of road geometry in autonomous driving systems. This role focuses on building next-generation large-scale vectorized HD mapping models that transform raw sensor data into structured, map-level representations of the environment. You will work closely with a multidisciplinary team of researchers and engineers at the intersection of computer vision, deep learning, and autonomous systems. The internship will involve designing, implementing, and evaluating state-of-the-art neural architectures for extracting vectorized representations of road layouts, lane topology, and scene structure from visual inputs.
San Jose, CA

 

Key Responsibilities

 
  • Design and develop Learning-based Bird's-Eye-View Perception Algorithms, specifically, 3D Road Geometry Reconstruction as Vector Maps and Road Topology Estimation from Vision.
  • Create and maintain datasets for training the network.
  • Develop evaluation metrics to confirm the efficacy of proposed algorithms.

 

Minimum Qualifications

 
  • Currently pursuing a Ph.D. or M.S. in Computer Science, Robotics, Electrical Engineering, or a related field.
  • Strong background in computer vision and deep learning.
  • Familiarity with Bird's-Eye-View (BEV) perception methods and relevant literature.
  • Understanding of state-of-the-art vision and learning techniques (e.g., transformers, CNNs, multi-view geometry).
  • Strong programming skills in Python and/or C++, with the ability to translate research ideas into working systems.
  • Experience with deep learning frameworks such as PyTorch and/or TensorFlow.

 

Bonus Qualifications​

  • Publications in top-tier venues such as CVPR, ICCV, ECCV, NeurIPS, ICLR, ICRA, or IROS.
  • Hands-on experience with Vectorized HD mapping or autonomous driving datasets (e.g., nuScenes, Waymo, Argoverse); Model optimization and deployment for real-time or edge systems; and 3D perception, multi-view geometry, or sensor fusion.
  • Experience improving model efficiency (e.g., pruning, quantization, TensorRT).

 

Years of Work Experience Required   0
Desired Start Date  8/31/2026
Internship Duration  3 Months
Position Keywords  Computer Vision, Autonomous Driving, HD Mapping 

Alternate Way to Apply

Send an e-mail to careers@honda-ri.com with the following:
- Subject line including the job number(s) you are applying for 
- Recent CV 
- A cover letter highlighting relevant background (Optional)

Please, do not contact our office to inquiry about your application status.