Search for: All records

Task planning is the problem of finding a discrete sequence of actions to achieve a goal. Unfortunately, task planning in robotic domains is computationally challenging. To address this, in our prior work, we explained how knowledge from a successful task solution can be cached for later use, as an “abstract skill.” Such a skill is represented as a trace of states (“road map”) in an abstract space and can be matched with new tasks on-demand. This paper explains how one can use a library of abstract skills, derived from past planning experience, to reduce the computational cost of solving new task planning problems. As we explain, matching a skill to a task allows us to decompose it into independent sub-tasks, which can be quickly solved in parallel. This can be done automatically and dynamically during planning. We begin by formulating this problem of “planning with skills” as a constraint satisfaction problem. We then provide a hierarchical solution algorithm, which integrates with any standard task planner. Finally, we experimentally demonstrate the computational benefits of the approach for reach-avoid tasks. 

Underwater navigation presents several challenges, including unstructured unknown environments, lack of reliable localization systems (e.g., GPS), and poor visibility. Furthermore, good-quality obstacle detection sensors for underwater robots are scant and costly; and many sensors like RGB-D cameras and LiDAR only work in-air. To enable reliable mapless underwater navigation despite these challenges, we propose a low-cost end-to-end navigation system, based on a monocular camera and a fixed single-beam echo-sounder, that efficiently navigates an underwater robot to waypoints while avoiding nearby obstacles. Our proposed method is based on Proximal Policy Optimization (PPO), which takes as input current relative goal information, estimated depth images, echo-sounder readings, and previous executed actions, and outputs 3D robot actions in a normalized scale. End-to-end training was done in simulation, where we adopted domain randomization (varying underwater conditions and visibility) to learn a robust policy against noise and changes in visibility conditions. The experiments in simulation and real-world demonstrated that our proposed method is successful and resilient in navigating a low-cost underwater robot in unknown underwater environments. The implementation is made publicly available at https://github.com/dartmouthrobotics/deeprl-uw-robot-navigation. 

In this paper, we discuss how to effectively map an underwater structure with a team of robots considering the specific challenges posed by the underwater environment. The overarching goal of this work is to produce high-definition, accurate, photorealistic representation of underwater structures. Due to the many limitations of vision underwater, operating at a distance from the structure results in degraded images that lack details, while operating close to the structure increases the accumulated uncertainty due to the limited viewing area which causes drifting. We propose a multi-robot mapping framework that utilizes two types of robots: proximal observers which map close to the structure and distal observers which provide localization for proximal observers and bird’s-eye-view situational awareness. The paper presents the fundamental components and related current results from real shipwrecks and simulations necessary to enable the proposed framework, including robust state estimation, real-time 3D mapping, and active perception navigation strategies for the two types of robots. Then, the paper outlines interesting research directions and plans to have a completely integrated framework that allows robots to map in harsh environments.