PhD Student · CU Boulder

Lorin Achey

I build multi-modal perception systems for autonomous vehicles and mobile robots — teaching machines to see, predict, and act in environments they have only partly observed.

See the research CV

Research directions

Generative occupancy & world models

Diffusion models that complete a 3D scene from partial observation, so a robot can plan against what is probably there rather than only what it has already seen.

Embodied scene understanding

Predicting where a carried object belongs in a home from the room layout, the person carrying it, and what little is known of their routine, so a robot can tidy or assist without being told where things go.

Multi-modal 3D perception

Fusing RGB-D, LiDAR, and RF signals into scene understanding that holds up in the cluttered, egocentric, partly-observed conditions real robots actually operate in.

Vision–Language–Action models

Unifying perception, language, and control so that grounded instructions become safe, explainable decisions on a real platform.

Watch the talk →

Risk-sensitive locomotion & navigation

Distributional reinforcement learning models the whole spread of outcomes rather than the expected return, so a quadruped can learn locomotion and navigation policies that account for risk directly.

Selected publications

All publications →

In review2026

ECHO: Embodied Camera Observations of Human Object Carrying

Xuefei Sun, Lorin Achey, Kali Hamilton, Alberto Speranzon, Gregory Grebe, Yonatan Bisk, Christoffer Heckman

3,805 human-annotated object-carrying episodes across 159 floors of 115 HM3D scenes. No single input modality is enough to predict where an object belongs.

arXiv

In review2026

RF-Modulated Adaptive Communication Improves Multi-Agent Robotic Exploration

Lorin Achey, Breanne Crockett, Christoffer Heckman, Bradley Hayes

Across 480+ simulated cave environments, cut distance travelled by up to 58% and exploration time by up to 52%.

arXiv

Autonomous Robots2026

Robust Robotic Exploration and Mapping Using Generative Occupancy Map Synthesis

Lorin Achey, Alec Reed, Brendan Crowe, Bradley Hayes, Christoffer Heckman

Autonomous Robots (Springer)

Deployed on a quadruped in real-world experiments: 24% better map fidelity around the robot and 76% better at range.

Diffusion pipeline predicting 3D occupancy at the exploration frontier

ICRA2025

Online Diffusion-Based 3D Occupancy Prediction at the Frontier with Probabilistic Map Reconciliation

Alec Reed, Lorin Achey, Brendan Crowe, Bradley Hayes, Christoffer Heckman

IEEE International Conference on Robotics and Automation (ICRA)

73% faster runtime with minimal accuracy loss, extending prediction across the whole map rather than just around the robot.