Topic

GPU-accelerated robotics

The use of GPUs and accelerated computing libraries to run robot perception, mapping, planning and control workloads, on workstations and on embedded modules.

Current clusters

build1 publisher

Four runtime conditions decide whether a ROS 2 depth image moves without a host copy

NVIDIA's CUDA buffer backend lets a standard ROS 2 message field carry GPU memory, and the same host, the same device, the same Linux user and a supported RMW all have to line up before the copies actually disappear.

Publishers:developer.nvidia.com

Reality

Evidence54
Adoption34
Hype gap+18
Incentives84
Confidence48

build1 publisher

NVIDIA repackages Isaac ROS setup and manipulation as skills an AI agent can call

Isaac ROS 5.0 ships agent-ready documentation, a standalone pick-and-place skill, and a FoundationPose library NVIDIA clocks at up to 5.5x faster. The part with the longest reach is an interface it contributed to ROS Lyrical itself.

Publishers:nvidianews.nvidia.com

Reality

Evidence38
Adoption35
Hype gap+25
Incentives88
Confidence45