SentiBotics Navigation SDK
Imitation learning-based autonomous robot navigation kit
The software development kit is designed for researchers and engineers working on autonomous robot navigation projects. The kit may be also used for educational purposes in universities and other education institutions.
Available as either a complete, ready-to-run robotics system that includes Neurotechnology's mobile reference platform prototype, or as a software-only option for integration into existing robotics hardware.
Robotic Platform Specifications for SentiBotics Navigation SDK
A robotics kit with ready-to-run mobile robot prototype is optionally available with SentiBotics Navigation SDK. The robotic hardware consists of:
Tracked mobile platform (two 17 W motors, 1.72 Nm torque) with accurate motor encoders.
- The platform includes inertial measurement unit (IMU) and is capable to execute precise movements. The Teensy-3.2 based platform controller integrates the data from motor encoders and IMU, two frontal sonars, and other sensors, and allows to execute smooth and accurate movements of the platform.
- Platform's construction allows to carry up to 10 kg (22 lbs) of payload.
- Intel NUC i5 on-board computer (RKE53427 board, Intel Core i5-3427U CPU running at 1.80GHz , 8 GB RAM, 64 GB SSD drive, 802.11n wireless network interface).
- Integrated Intel Movidius Neural Compute Stick (NCS) allows to efficiently run various neural network-based computer vision models with almost zero CPU load.
- Battery (20 A⋅h 4-cell LiFePO4) with 4 A charger.
- Autonomous recharging hardware with a docking station.
RGB camera and 3D sensor:
- long range Asus Xtion Pro Live - depth measurement range 1 - 3.5 m (3'3" - 11'6").
- Control pad for manual control of the robot.
Note that the robotic platform is designed for in-doors use in office-like or laboratory environment.