Daniel Morton

Hello, I'm Daniel Morton

I am a PhD candidate at Stanford University, where I work with Marco Pavone in the Autonomous Systems Lab. I’m interested in efficient planning and modeling methods for robotic manipulation, with an emphasis on space and novel hardware. Before Stanford, I worked with Rob Shepherd in the Organic Robotics Lab at Cornell. I am also a current 2024 NASA Space Technology Graduate Research Fellow, and was a 2022 NSF Graduate Research Fellow.

Scholar Github Linkedin

Publications

Safe, Task-Consistent Manipulation with Operational Space Control Barrier Functions

Daniel Morton, Marco Pavone

IROS, 2025 [Submitted]

We introduce an Operational Space Control Barrier Function (OSCBF) framework that integrates safety constraints while preserving task-consistent behavior during manipulation. Our approach scales to hundreds of simultaneous constraints while retaining real-time control rates, ensuring collision avoidance, singularity prevention, and workspace containment even in highly cluttered and dynamic settings.

Project Page PDF arXiv Code

Task-Driven Manipulation with Reconfigurable Parallel Robots

Daniel Morton, Mark Cutkosky, Marco Pavone

IROS, 2024

We present a manipulation planning method for ReachBot, a new form of space robot employing extendable booms for mobility in Martian lava tubes. Via a two-part optimization-based method, we determine the configuration of the robot (where to place the booms) as well as how much tensile force should be applied in each boom. Through this, we can reliably complete tasks even despite uncertainty, disturbances, and stochastic failure modes.

Project Page PDF arXiv Code

Open X-Embodiment: Robotic Learning Datasets and RT-X Models

Open X-Embodiment Collaboration

ICRA, 2024 Best Conference Paper

We introduce the Open X-Embodiment Dataset, the largest robot learning dataset to date with 1M+ real robot trajectories, spanning 22 robot embodiments. We train large, transformer-based policies on the dataset (RT-1-X, RT-2-X) and show that co-training with our diverse dataset substantially improves performance.

Project Page PDF arXiv

DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset

Alexander Khazatsky, Karl Pertsch, ... , Daniel Morton, ... , Sergey Levine, Chelsea Finn

RSS, 2024

We introduce DROID, the most diverse robot manipulation dataset to date. It contains 76k demonstration trajectories or 350 hours of interaction data, collected across 564 scenes and 84 tasks by 50 data collectors in North America, Asia, and Europe over the course of 12 months. We demonstrate that training with DROID leads to policies with higher performance and improved generalization ability.

Project Page PDF arXiv

Autonomous Material Composite Morphing Wing

Daniel Morton, Artemis Xu, Alberto Matute, Robert Shepherd

JCM, 2023

We developed a novel soft robotic morphing wing, capable of three-degree-of-freedom morphing (twist, camber, and extension) via an elastomeric conformal lattice with embedded optical strain sensors.

PDF arXiv

Projects & Demos

Drone Fencing

Daniel Morton, Rika Antonova, Marco Pavone

Stanford Robotics Center Opening, November 2024

Demonstrating reactive collision avoidance with control barrier functions, via a drone dodging a saber

Project Page Code

Software

CBFpy: Control Barrier Functions in Python and Jax

Daniel Morton

An easy-to-use and high-performance framework for constructing and solving Control Barrier Functions (CBFs) and Control Lyapunov Functions (CLFs)

Documentation Code