Robot Grasping in a Heavily Cluttered Environment
Korea Advanced Institute of Science and Technology (KAIST) student Dongwon Son has recently published interesting research about reactive grasping in a heavily cluttered environment in IEEE Robotics and Automation Letters.
![grasping-in-a-heavily-cluttered-environment-pic-1.jpg](https://minio.news.mecharithm.com:443/mecharithm/grasping_in_a_heavily_cluttered_environment_pic_1_bb12468632.jpg)
This study proposed a closed-loop framework for predicting the six-degree-of-freedom (dof) grasp in a heavily cluttered environment using vision observations.
![robot-grasping-prediction-results.jpg](https://minio.news.mecharithm.com:443/mecharithm/robot_grasping_prediction_results_1d6e2cf5b8.jpg)
Experimental results on a robot in an environment with a lot of clutter showed that the grasping success rate had improved quantitatively compared to the previous algorithms. Additionally, the framework is able to respond qualitatively to a dynamic change in the environment and clean up the table successfully.
![experimental-results-robot-grasping.jpg](https://minio.news.mecharithm.com:443/mecharithm/experimental_results_robot_grasping_013d0d7c28.jpg)
Their method involves formulating the grasping problem as a Hidden Markov Model and applying a particle filter in order to infer grasp. To make the particle filter process possible, they developed a lightweight Convolutional Neural Network (CNN) model for Real-time evaluation and initialization of grasp samples.
![particle-process-in-robot-grasping.jpg](https://minio.news.mecharithm.com:443/mecharithm/particle_process_in_robot_grasping_6d262af36c.jpg)