Voxel-based sim2real author flags two hurdles: voxel resolution vs speed and data scarcity
chris_j_paxton · x · 2026-11-05
Robotics researcher jwang771 responds to praise calling their voxel-based sim2real method 'the future of robotics simulation,' candidly laying out open challenges:
- Architecture: the voxel approach thrives on compact workspaces, but larger scenes hit the perennial voxel-resolution-vs-speed tradeoff, possibly mitigated with sparse voxel kernels. The team is also building an egocentric version mounted on the robot base for room-scale simulation of mobile manipulation.
- Data availability: the author believes the model will work with the right data, but collecting it may take substantial effort (text truncated).
Overall confident in the method's potential while flagging concrete obstacles on the path to real-world deployment.
More from Embodied
- Open-source robotics talk at Wawtech Warsaw aims to get software devs building robots — kamathsblog · 2026-11-05
- PhD student blogs on challenges of latent action models for robotics pretraining — EugeneVinitsky · 2026-11-05
- Liquidating ~18 humanoid robots in SF: Unitree G1/H1/R1, AGIbot, Booster, EngineAI in stock — cixliv · 2026-11-05
- Nothing CEO says mysterious AI-first device launches next month — TechCrunch AI · 2026-11-05
- Pretraining Makes Robot Policies Reliable but Hurts Posttraining, New Paper Finds — siddkaramcheti · 2026-11-05
- XR Blocks team runs talk, demos and 'World as a Canvas' workshop at UIST 2026 — DuRuofei · 2026-11-05