SympLER

About

Current demographics and reports regarding the absence of caring staff make the need for intelligent robots that can act as general-purpose assistants imperative. While robot learning holds the promise of endowing robots with complex skills through experience and interaction with the environment, most methods overfit single tasks that do not generalize well in the non-stationary real world. Conversely, humans constantly learn while building on top of existing knowledge.

Lifelong robot learning stipulates that an agent can form representations that are useful for learning a series of tasks continually, avoiding catastrophic forgetting of earlier skills. To this end, robots need to compose a series of behaviors for synthesizing complex courses of action. For the sake of efficiency, lifelong agents have to be able to build on previous representations for learning new skills while avoiding the two key issues of task interference and catastrophic forgetting. Moreover, explainability is a crucial component for increasing the trustworthiness of AI robots during their interaction with non-expert users. Robots need to be able to explain to non-expert users similarities found across tasks throughout their training life, and, for example, even to map their actions while executing a task into natural language explanations.

In the symposium of Lifelong Explainable Robot Learning (SYMPLER), we will address these crucial challenges by bringing together young and established researchers to discuss persisting open problems related to:

• Robust forward and backward transfer of skills;

• Mitigation of catastrophic forgetting and task-interference;

• Generalization across different tasks;

• Explainability of skills and task similarities;

• Natural language explanations of robots' behavior.

Invited speakers

Hotel Pomander

Frauentorgraben 11,

 90443 Nuremberg