STMicroelectronics and Leopard Imaging have introduced a multimodal vision module designed for humanoid and advanced robotics systems. The module combines 2D imaging, 3D depth sensing, and motion perception capabilities with NVIDIA Holoscan Sensor Bridge technology for integration with NVIDIA Jetson platforms and the NVIDIA Isaac robot development platform.

The module incorporates several STMicroelectronics sensors, including the VB1940 automotive-grade RGB-IR 5.1-megapixel image sensor with rolling and global shutter modes, the LSM6DSV16X 6-axis inertial measurement unit with machine-learning capabilities, and the VL53L9CX dToF LiDAR module for 3D depth sensing up to 9 meters with 54 x 42 zone resolution.

"Humanoid robotics is moving beyond research projects and demonstrations to deliver powerful new machines for a wide range of roles in manufacturing and automotive factories, logistics and warehousing, as well as retail and customer service," said Marco Angelici, Vice-President of Marketing and Application for Analog Power MEMS and Sensors at STMicroelectronics.

Bill Pu, CEO of Leopard Imaging, stated that accessing STMicroelectronics sensors directly within the ecosystem has allowed the company to standardize data acquisition for humanoid robot vision systems. The module enables real-time sensor data ingestion over ethernet and includes APIs, AI algorithms, sample applications, and simulation environments.

The VL53L9CX LiDAR module provides a 55°x42° field of view with 1° angular resolution and can operate at up to 100 frames per second. The LSM6DSV16X IMU includes sensor-fusion low-power capabilities and electrostatic sensing for user-interface detection.

STMicroelectronics continues its partnership with NVIDIA as a robotics and edge AI partner, integrating sensors, drivers, actuators, and development tools into the NVIDIA robotics ecosystem. The information is based on a company press release.