LoHoRavens: A Long-Horizon Language-Conditioned Benchmark for Robotic Tabletop Manipulation
This provides a benchmark for researchers in robotics and AI to develop better models for long-horizon tabletop manipulation tasks, though it is incremental as it builds on existing work in embodied agents and LLMs.
The authors tackled the lack of public benchmarks for long-horizon reasoning in language-conditioned robotic tabletop manipulation by releasing LoHoRavens, a simulation benchmark covering various reasoning aspects, and found that baseline methods struggle with some tasks, indicating ongoing challenges.
The convergence of embodied agents and large language models (LLMs) has brought significant advancements to embodied instruction following. Particularly, the strong reasoning capabilities of LLMs make it possible for robots to perform long-horizon tasks without expensive annotated demonstrations. However, public benchmarks for testing the long-horizon reasoning capabilities of language-conditioned robots in various scenarios are still missing. To fill this gap, this work focuses on the tabletop manipulation task and releases a simulation benchmark, \textit{LoHoRavens}, which covers various long-horizon reasoning aspects spanning color, size, space, arithmetics and reference. Furthermore, there is a key modality bridging problem for long-horizon manipulation tasks with LLMs: how to incorporate the observation feedback during robot execution for the LLM's closed-loop planning, which is however less studied by prior work. We investigate two methods of bridging the modality gap: caption generation and learnable interface for incorporating explicit and implicit observation feedback to the LLM, respectively. These methods serve as the two baselines for our proposed benchmark. Experiments show that both methods struggle to solve some tasks, indicating long-horizon manipulation tasks are still challenging for current popular models. We expect the proposed public benchmark and baselines can help the community develop better models for long-horizon tabletop manipulation tasks.