3D Vision-Guided Soft Sack Depalletizing
Project background: Automated and intelligent food production line has become an important means to improve food production. Traditional manual palletizing not only has high cost, but also has the problem of high labor intensity and high risk of injury. Especially in some repetitive, labor-intensive operations, such as food packaging and handling, the introduction of automated palletizing equipment can significantly reduce labor costs, while improving the safety of the work environment.
- Project advantages:
- Higher versatility, training deep learning models based on DexForce self-developed DexVerse™ embodiments intelligent engine, supporting adaptive learning and general recognition of 3D visual large models of various depalletizing materials;
- Support to configure multiple product models at the same time, and switch operations according to robot signals; No need to stop production to collect annotated data, 8 hours to complete the deep learning model training of the new workpiece, quickly on-line production;
- Zero code, zero programming, directly adjust the parameters to achieve visual positioning, the fastest 5 minutes to complete the visual configuration, 20 minutes to cooperate with the robot to grasp debugging;
- Application results
Combined with Kingfisher intelligent camera, a new industrial logistics pure visual imaging perception kit based on 3D VLA (3D Vision Language Action) large model is created to support the de-stacking scene towards AnyGrasp. Instead of customized data calibration and task programming for different operating objects. With stronger core capabilities, higher versatility, faster delivery, and better application costs.