Continual/lifelong learning for long-term robotic operation
Establish practical continual or lifelong learning methods for robotics that enable robots to operate over long periods while adapting to new tasks and environments without sacrificing previously acquired capabilities, thereby overcoming catastrophic forgetting during sequential task acquisition.
References
This long-term adaptability, known as continual or lifelong learning, remains an open challenge in robotics despite decades of research.
While the online actor responds to current observations, handling changes in task goals or newly introduced instructions during an episode remains unexplored.
The open problem is cumulative improvement with bounded verification costs and without sacrificing service continuity or safety.
However, current approaches mainly focus on memory storage and retrieval, while autonomous organization, knowledge consolidation, and adaptive updating remain open challenges.
However, fully autonomous self-evolving memory has not yet been demonstrated in current VLA systems [1].
Learning continually from a non-stationary stream of experience, as humans do, remains a major open challenge.