DKPROMPT: Domain Knowledge Prompting Vision-Language Models for Open-World Planning

Vision-language models (VLMs) have been applied to robot task planning problems, where the robot receives a task in natural language and generates plans based on visual inputs. While current VLMs have demonstrated strong vision-language understanding capabilities, their performance is still far from being satisfactory in planning tasks. At the same time, although classical task planners, such as PDDL-based, are strong in planning for long-horizon tasks, they do not work well in open worlds where unforeseen situations are common. In this paper, we propose a novel task planning and execution framework, called DKPROMPT, which automates VLM prompting using domain knowledge in PDDL for classical planning in open worlds. Results from quantitative experiments show that DKPROMPT outperforms classical planning, pure VLM-based and a few other competitive baselines in task completion rate.

Guided Dyna-Q for Mobile Robot Exploration and Navigation

Model-based reinforcement learning (RL) enables an agent to learn world models from trial-and-error experiences toward achieving long-term goals. Automated planning, on the other hand, can be used for accomplishing tasks through reasoning with declarative action knowledge. Despite their shared goal of completing complex tasks, the development of RL and automated planning has mainly been isolated due to their different modalities of computation. Focusing on improving model-based RL agent's exploration strategy and sample efficiency, we develop Guided Dyna-Q (GDQ) to enable RL agents to reason with action knowledge to avoid exploring less-relevant states toward more efficient task accomplishment. GDQ has been evaluated in simulation and using a mobile robot conducting navigation tasks in an office environment. Results show that GDQ reduces the effort in exploration while improving the quality of learned policies.