DreamZero is a World Action Model by NVIDIA that replaces the Vision-Language backbone common in VLAs with a video diffusion model to inherit richer physical priors. I compare DreamZero with π0.5 across 12 tasks in Isaac Sim on a DROID setup.
I use reinforcement learning in NVIDIA Isaac Lab to train Boston Dynamics' Spot to stand and move using only its hind legs. Despite several challenges, I achieve zero-shot sim-to-real transfer and deploy the policy directly on real hardware.
Grievous is a low-cost mobile manipulation platform built on XLeRobot, extended with onboard SO-101 leader arms for fast in-place teleoperation. We finetune SmolVLA on pick-and-place and dusting tasks collected in lab environment and showcase current …
I recently joined the Center for Autonomy at UT Austin as a Postdoctoral Fellow, returning to the robotics frontier after co-founding and scaling a defense AI startup to seven-figure funding.
From voice command to synchronized flip: we show our early autonomous mission planning work that grew into Multi AI, including Tello drone choreography and a loyal wingman simulation for unmanned-manned teaming.
What if a drone could build structures humans can't reach? We investigate integrating underactuated multicopters with 3D printing for large-scale remote additive manufacturing — demonstrating aerial positioning accuracy competitive with ground-based …
In recent years, large-scale and fully-remote 3D printing with robots has garnered significant interest in construction applications. Combining the design freedom of 3D printing with a robot's versatility offers unique and promising opportunities for …
This paper presents a self-supervised Learning from Learned Hallucination (LfLH) method to learn fast and reactive motion planners for ground and aerial robots to navigate through highly constrained environments. The recent Learning from …
Standard path planners proved insufficient for dense multi-drone environments. We develop custom algorithms on top of EGO-Planner to enable robust obstacle avoidance in the Texas Robotics motion capture space, supporting advanced multi-agent …
Current limitations in vertical and horizontal mobility for ground robots in 3D printing of medium to large-scale objects have recently led to the development of a 3D printing hexacopter testbed at the University of Texas at Austin. This testbed can …