Grasp-type Recognition Leveraging Object Affordance
This work addresses a specific challenge in robot teaching by enhancing recognition accuracy, but it is incremental as it builds on existing methods with a simple correction pipeline.
The paper tackled grasp-type recognition from a single RGB image and object name in robot teaching by combining a CNN with object affordance priors, achieving improved performance over CNN-only and affordance-only methods.
A key challenge in robot teaching is grasp-type recognition with a single RGB image and a target object name. Here, we propose a simple yet effective pipeline to enhance learning-based recognition by leveraging a prior distribution of grasp types for each object. In the pipeline, a convolutional neural network (CNN) recognizes the grasp type from an RGB image. The recognition result is further corrected using the prior distribution (i.e., affordance), which is associated with the target object name. Experimental results showed that the proposed method outperforms both a CNN-only and an affordance-only method. The results highlight the effectiveness of linguistically-driven object affordance for enhancing grasp-type recognition in robot teaching.