Long-Horizon Robotic Manipulation
Overview
Long-horizon robotic manipulation concerns tasks that require many dependent actions, such as assembling furniture, preparing food, or moving objects through changing environments. Common approaches combine hierarchical planning and reusable skills with vision-language-action policies, world models, symbolic task representations, and memory of past actions or object states. Researchers train these systems with demonstrations, reinforcement learning, simulated experience, and human corrections, and evaluate them in multi-stage benchmarks and real-robot settings. A central challenge is that strong performance on individual skills does not guarantee reliable task completion: errors can accumulate at skill transitions, while memory, recovery, and safety remain difficult to evaluate and generalize.
Latest papers
435 papers88 papers in the last four weeks, up 49% on the four weeks before. 0.5% of all new papers.