On-board Planner Research Articles

Autonomous robotics is driving Perseverance rover's progress on Mars.

NASA's Perseverance rover uses robotic autonomy to achieve its mission goals on Mars. Its self-driving autonomous navigation system (AutoNav) has been used to evaluate 88% of the 17.7-kilometer distance traveled during its first Mars year of operation. Previously, the maximum total autonomous distance evaluated was 2.4 kilometers by the Opportunity rover during its 14-year lifetime. AutoNav has set multiple planetary rover records, including the greatest distance driven without human review (699.9 meters) and the greatest single-day drive distance (347.7 meters). The Autonomous Exploration for Gathering Increased Science (AEGIS) system analyzes wide-angle imagery onboard to autonomously select targets for observations by the SuperCam instrument, a multimode sensor suite capable of millimeter-scale geochemical and mineralogical analysis. AEGIS enables observations of scientifically interesting targets during or immediately after long drives without the need for ground communication. OnBoard Planner (OBP) is a scheduling capability planned for operational use in September 2023 that has the potential to reduce energy usage by up to 20% and complete drive and arm-contact science campaigns in 25% fewer days on Mars. This paper presents an overview of the AutoNav, AEGIS, and OBP capabilities used on Perseverance.

Heuristic search via graphical structure in temporal interval-based planning for deep space exploration

Operations of conventional spacecraft used to be planned on ground and are uploaded as telecommands and executed on board at due time. However, because of difficulties in communicating with distant spacecraft, direct human control for the spacecraft is infeasible. Therefore, great hopes are placed on automated planning techniques to enhance the security of the spacecraft. By deciding a coon, as to support opportunistic science, the planner is mplex set of activities or states, an onboard planner is able to effectively arrange the daily tasks on a spacecraft. In additialso required to respond in the shortest possible time. Typically, to better characterize the spacecraft, the timeline-based knowledge representation benefits from its powerful ability to describe time and temporal behaviors, which is essential to effectively address real world problems. Compliant with the representation method, an elegant approach is devised for search guidance and solving problems efficiently in space-like contexts. Specifically, the key technique we build on is the heuristic estimate strategy based on a graphical structure defined in the model. Furthermore, a search algorithm joint with the heuristic function is proposed to avoid redundant work. By evaluating the branching nodes, this approach is able to prune irrelevant search space and make improvements in onboard planning efficiency. Our experiments exhibit an excellent performance on tested instances compared to Europa2.

COLA2: A Control Architecture for AUVs

This paper presents a control architecture for an autonomous underwater vehicle (AUV) named the Component Oriented Layer-based Architecture for Autonomy (COLA2). The proposal implements a component-oriented layer-based control architecture structured in three layers: the reactive layer, the execution layer, and the mission layer. Concerning the reactive layer, to improve the vehicle primitives' adaptability to unknown changing environments, reinforcement learning (RL) techniques have been programmed. Starting from a learned-in-simulation policy, the RL-based primitive cableTracking has been trained to follow an underwater cable in a real experiment inside a water tank using the Ictineu AUV. The execution layer implements a discrete event system (DES) based on Petri nets (PNs). PNs have been used to safely model the primitives' execution flow by means of Petri net building block (PNBBs) that have been designed according to some reachability properties showing that it is possible to compose them preserving these qualities. The mission layer describes the mission phases using a high-level mission control language (MCL), which is automatically compiled into a PN. The MCL presents agreeable properties of simplicity and structured programming. MCL can be used to describe offline imperative missions or to describe planning operators, in charge of solving a particular phase of a mission. If planning operators are defined, an onboard planner will be able to sequence them to achieve the proposed goals. The whole architecture has been validated in a cable tracking mission divided in two main phases. First, the cableTracking primitive of the reactive layer has been trained to follow a cable in a water tank with the Ictineu AUV, one of the research platforms available in the Computer Vision and Robotics Group (VICOROB), University of Girona, Girona, Spain. Second, the whole architecture has been proved in a realistic simulation of a whole cable tracking mission.