Semantic learning from keyframe demonstration using object attribute constraints

Learning from demonstration is an approach that allows users to personalize a robot's tasks. While demonstrations often focus on conveying the robot's motion or task plans, they can also communicate user intentions through object attributes in manipulation tasks. For instance, users might want to teach a robot to sort fruits and vegetables into separate boxes or to place cups next to plates of matching colors. This paper introduces a novel method that enables robots to learn the semantics of user demonstrations, with a particular emphasis on the relationships between object attributes. In our approach, users demonstrate essential task steps by manually guiding the robot through the necessary sequence of poses. We reduce the amount of data by utilizing only robot poses instead of trajectories, allowing us to focus on the task's goals, specifically the objects related to these goals. At each step, known as a keyframe, we record the end-effector pose, object poses, and object attributes. However, the number of keyframes saved in each demonstration can vary due to the user's decisions. This variability in each demonstration can lead to inconsistencies in the significance of keyframes, complicating keyframe alignment to generalize the robot's motion and the user's intention. Our method addresses this issue by focusing on teaching the higher-level goals of the task using only the required keyframes and relevant objects. It aims to teach the rationale behind object selection for a task and generalize this reasoning to environments with previously unseen objects. We validate our proposed method by conducting three manipulation tasks aiming at different object attribute constraints. In the reproduction phase, we demonstrate that even when the robot encounters previously unseen objects, it can generalize the user's intention and execute the task.

Limited Impact of Object Attributes on Event-related Potentials During an Implicit Word Reading Task

BACKGROUND

Previous research in cognitive science has focused on the encoding and activation of sensory-based object knowledge in the brain during language comprehension, including aspects such as appearance, movement, and taste.

OBJECTIVE

To investigate how different object-related attributes affect event-related potentials (ERPs), specifically the N400 component, during word processing in an implicit task setting.

METHOD

We embedded a set of 420 critical nouns within a list of 2,745 total words and asked 240 participants to read each one, but to respond only to words denoting colors. We categorized each noun by attributes such as familiarity, smell, pain, taste, sound, graspability, and motion. We focused primarily on changes in the N400 component, indicative of semantic processing, across nouns with different attributes.

RESULTS

The least familiar stimuli elicited the strongest N400 response, indicating significant ERP variability across familiarity levels with more positive amplitudes for highly familiar stimuli. Among the attributes examined, only the attribute of smell demonstrated a notable, though isolated, increase in N400 amplitude. Other attributes, including pain, taste, sound, graspability, and visual motion showed no significant differences in N400 responses, suggesting a minimal influence on semantic processing in this context.

CONCLUSION

These results suggest that the specific sensory attributes of objects have limited influence on the N400 component of ERPs in implicit reading tasks, highlighting the complexity of semantic networks in cognitive processing. The subtlety of ERP modulations driven by object-related attributes points to the need for further exploration into how these attributes interact within semantic networks during cognitive tasks.