Perception‐aware autonomous mast motion planning for planetary exploration rovers

Abstract

Highly accurate real-time localization is of fundamental importance for the safety and efficiency of planetary rovers exploring the surface of Mars. Mars rover operations rely on vision-based systems to avoid hazards as well as plan safe routes. However, vision-based systems operate on the assumption that sufficient visual texture is visible in the scene. This poses a challenge for vision-based navigation on Mars where regions lacking visual texture are prevalent. To overcome this, we make use of the ability of the rover to actively steer the visual sensor to improve fault tolerance and maximize the perception performance. This paper answers the question of where and when to look by presenting a method for predicting the sensor trajectory that maximizes the localization performance of the rover. This is accomplished by an online assessment of possible trajectories using synthetic, future camera views created from previous observations of the scene. The proposed trajectories are quantified and chosen based on the expected localization performance. In this work, we validate the proposed method in field experiments at the Jet Propulsion Laboratory (JPL) Mars Yard. Furthermore, multiple performance metrics are identified and evaluated for reducing the overall runtime of the algorithm. We show how actively steering the perception system increases the localization accuracy compared to traditional fixed-sensor configurations.

Slip-Based Autonomous ZUPT Through Gaussian Process to Improve Planetary Rover Localization

“…VO is an accurate and reliable source of information for slip estimation; however, it is computationally expensive for planetary rovers. Even with the field-programmable gate array (FPGA) processors [15], the other limitations of VO arise that it suffers from low-feature terrains and it relies on proper lighting conditions [16]. Similarly, insufficiently detected and tracked features may lead to poor accuracy of motion estimate [5].…”

“…The tracking system is able to provide reliable solution in feature rich areas whereas it suffers in the areas with a lack of detectable and trackable features. This is a common issue of visual-based localization approaches because these approaches require reasonable distinct visual features in view to operate accurately [2], [16], [44].…”

Uncertainty-aware Safe Exploratory Planning using Gaussian Process and Neural Control Contraction Metric

“…To learn an accurate model of the vehicle, we have to safely drive the vehicle to every part of the environment and collect data about the friction while remaining safe. Similarly, safe exploratory planning is also a key yet challenging problem in many engineering domains such as Mars rover exploration as in (Ono et al, 2018;Ahmadi et al, 2020;Strader et al, 2020) and delivery drones as in (Cao et al, 2017;Berkenkamp and Schoellig, 2015). We propose a novel framework to solve such uncertaintyaware safe exploratory problems by combining neural Control Contraction Metric (CCM) (cf.…”

Where to Map? Iterative Rover-Copter Path Planning for Mars Exploration

“…The rover's remote sensing capability is strongly impacted by localization performance since the accumulated errors in rover positions impose challenges in targeted observations after a few drives. Perception-aware planning is one of the effective methods to improve the performance of dead-reckoning-based localization [5], [6], [7], [8], [9]. It aims at improving the perception results by actively choosing future measurement targets.…”

“…It aims at improving the perception results by actively choosing future measurement targets. For example, the works in [8], [9] improved the performance of VO localization by actively choosing timing and camera direction to obtain an optimal image sequence using the predictive perception technique. This problem is typically approached by Partially Observable Markov Decision Process (POMDP), or belief-space planning [10], [11], [12], [13], [14], where the planner chooses optimal actions under motion and sensing uncertainty.…”