SympLER
1st Symposium On Lifelong Explainable Robot Learning
December 5th - 6th 2023 @ Hotel Pomander (Nürnberg)
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
Schedule
Day 1 (05.12)
9:00 - 9:30
Opening presentation
SYMPLER Organizers
Welcome
9:30 - 10:30
Invited talk
Alberto Maria Metelli
Explaining Human Intentions through Inverse Reinforcement Learning
10:30 - 11:00
Coffee Break
11:00 - 12:00
Invited talk
Martin Waltz
Local Path Planning in Transportation using Reinforcement Learning
12:00 - 13:00
Spotlight research talks
Speakers:
Ahmed Hendawy (TU Darmstadt)
Aryaman Reddi (TU Darmstadt)
Sebastian Griesbach (Uni Würzburg)
Oliver Järnefelt (Uni Würzburg)
LiteRL group
13:00 - 14:00
Lunch Break
15:00 - 16:00
Invited talk
Martin Mundt
Robust, Adaptive, Sustainable: The Synergy of Lifelong Intelligence
16:00 - 16:30
Coffee Break
16:30 - 17:00
Spotlight Research Talks
Jose Luis Holgado Alvarez (Uni Würzburg)
Mahdi Kallel (Uni Würzburg)
LiteRL group
17:00 - 18:00
Roundtable discussion
All participants
Day 2 (06.12)
08:30 - 10:30
Brainstorming session
LiteRL and PEARL groups
10:30 - 11:00
Coffee Break
11:00 - 12:00
Invited talk
Christoph Steup
Reliable Outdoor Robotics: Challenges and Solutions using Computational Intelligence
12:00 - 13:00
Invited talk
Wolfram Burgard
Probabilistic and Deep Learning Techniques for Robot Navigation and Automated Driving
13:00 - 14:00
Lunch Break
14:00 - 15:30
Spotlight research talks
Speakers:
Snehal Jauhri (TU Darmstadt)
Jiayun Li (TU Darmstadt)
Zechu (Steven) Li (MIT, TU Darmstadt)
Rickmer Krohn (TU Darmstadt)
Sohar Rudra (TU Darmstadt)
Ali Younes (TU Darmstadt)
PEARL group
15:30 - 16:00
Coffee Break
16:00 - 17:00
Roundtable discussion and concluding remarks
All participants
17:00 --
Social activity
All participants
Photo album of the event
Organizers
PEARL & Lite RL