Edge-intelligent vision-based robotic manipulation for real-time pick-and-place in dynamic industrial environments

Robust perception, fast decision-making, and reliable closed-loop control under uncertainty are necessary for vision-based robotic manipulation in dynamic industrial settings. An edge-intelligent robotic manipulation framework for pick-and-place tasks is presented in this work. It combines perception, calibration, motion planning, and control into a single simulation-based closed-loop architecture. To lower latency and increase robustness in dynamic circumstances, the suggested system makes use of a lightweight CNN-based perception module, calibration-aware SE(3) transformation refinement, and edge-enabled execution logic. To improve generalization under occlusion, light change, and object pose uncertainty, a data-centric enrichment technique is employed. Using a Monte Carlo technique and several trials in various industrial contexts, the framework is assessed in a high-fidelity simulation environment. Task success rate, latency, and robustness under the same settings have all improved when compared to current robotic manipulation baselines. Furthermore, without claiming full industrial implementation, a small-scale qualitative real-world validation (18 grip trials) is carried out to evaluate transferability. The outcomes demonstrate the efficacy of combining edge intelligence with closed-loop robotic control by confirming consistent behavior throughout simulation and limited physical testing.