SegICP-DSR: Dense Semantic Scene Reconstruction and Registration
This work addresses the challenge of precise object manipulation for robotics in cluttered, unstructured settings, representing an incremental improvement over prior methods.
The paper tackled the problem of enabling autonomous robotic manipulation in unstructured environments by developing SegICP-DSR, a real-time algorithm for dense semantic scene reconstruction and pose estimation, achieving mm-level accuracy (7.9 mm, σ=7.6 mm and 1.7 deg, σ=0.7 deg) and a 97% success rate in identifying object poses.
To enable autonomous robotic manipulation in unstructured environments, we present SegICP-DSR, a real- time, dense, semantic scene reconstruction and pose estimation algorithm that achieves mm-level pose accuracy and standard deviation (7.9 mm, σ=7.6 mm and 1.7 deg, σ=0.7 deg) and suc- cessfully identified the object pose in 97% of test cases. This represents a 29% increase in accuracy, and a 14% increase in success rate compared to SegICP in cluttered, unstruc- tured environments. The performance increase of SegICP-DSR arises from (1) improved deep semantic segmentation under adversarial training, (2) precise automated calibration of the camera intrinsic and extrinsic parameters, (3) viewpoint specific ray-casting of the model geometry, and (4) dense semantic ElasticFusion point clouds for registration. We benchmark the performance of SegICP-DSR on thousands of pose-annotated video frames and demonstrate its accuracy and efficacy on two tight tolerance grasping and insertion tasks using a KUKA LBR iiwa robotic arm.