2027 Internship State Estimation, Learned Mapping & Semantic SLAM

The role

You will prototype learned SLAM and mapping methods to help autonomous excavators understand terrain. You will work with lidar and camera data to build semantic maps and evaluate performance against baselines.

What you will do

• Prototype learned SLAM and mapping methods
• Fuse lidar and camera segmentation into consistent 3D semantic maps
• Develop methods that handle changing terrain, moving material, sparse returns, dust, occlusion, and perceptual aliasing
• Train models on fleet lidar and camera data
• Build evaluation pipelines to compare mapping and localization performance
• Work with perception and planning teams to identify map properties for downstream decisions
• Deliver a documented prototype, experimental results, and recommendations

Required qualifications

• Pursuing a BS, MS, or PhD in computer science, robotics, electrical engineering, or a related field, or equivalent research or industry experience
• Strong Python skills and hands-on model training experience with PyTorch or a similar framework
• Solid understanding of 3D geometry, coordinate frames, and transforms
• Familiarity with SLAM and mapping fundamentals, point clouds, or depth data
• Comfort with messy sensor data and designing experiments

Nice to have

• Research or project experience in learned SLAM, semantic mapping, or 3D scene understanding
• Experience with neural scene representations, such as NeRFs, 3D Gaussian splatting, neural occupancy, or signed distance fields
• Experience applying vision foundation models, such as DINOv2 or SAM, to 3D or robotics problems
• Experience with lidar processing or multi-sensor fusion
• Exposure to autonomous vehicle, off-road, or field robotics data
• Familiarity with Rust or C++, and ROS or similar robotics middleware

About the company

Bedrock retrofits heavy equipment like excavators with autonomy to help contractors safely take on more projects. The team includes veterans from Waymo, Segment, and Uber Freight.