Distributed Control of Multi-Robot Systems Engaged in Tightly Coupled Tasks

Abstract

NASA mission concepts for the upcoming decades of this century include exploration of sites such as steep cliff faces on Mars, as well as infrastructure deployment for a sustained robotic/manned presence on planetary and/or the lunar surface. Single robotic platforms, such as the Sojourner rover successfully flown in 1997 and the Mars Exploration Rovers (MER) which landed on Mars in January of 2004, have neither the autonomy, mobility, nor manipulation capabilities for such ambitious undertakings. One possible approach to these future missions is the fielding of cooperative multi-robot systems that have the required onboard control algorithms to more or less autonomously perform tightly coordinated tasks. These control algorithms must operate under the constrained mass, volume, processing, and communication conditions that are present on NASA planetary surface rover systems. In this paper, we describe the design and implementation of distributed control algorithms that build on our earlier development of an enabling architecture called CAMPOUT (Control Architecture for Multi-robot Planetary Outposts). We also report on some ongoing physical experiments in tightly coupled distributed control at the Jet Propulsion Lab in Pasadena, CA where in the first study two rovers acquire and carry an extended payload over uneven, natural terrain, and in the second three rovers form a team for cliff access.

Observability-based consistent EKF estimators for multi-robot cooperative localization

“…1 In the standard formulation of CL, the state vector comprises the N robot poses expressed in the global frame of reference. Thus, at time-step k the state vector is given by…”

“…In order for multi-robot teams to navigate autonomously and successfully perform tasks such as exploration [1], surveillance [2], and search and rescue [3], they must be able to determine their positions and orientations (poses) precisely. In GPS-denied areas and in the absence of robust landmarks, teams of robots can still localize by sharing relative robot-torobot measurements and jointly estimating their poses [4][5][6].…”

A hybrid estimation framework for Cooperative Localization under communication constraints

“…T , is the state of robot i, which generates M i k scalar measurements at time-step k. In this formulation, we assume a statistical motion model (e.g., the constant-velocity model [15]), in which the only control input is the system noise (see (1)). This allows us to treat both proprioceptive (linear and rotational velocity) and exteroceptive (relative distance/bearing/orientation) measurements, identically.…”

“…For robot teams navigating in GPS-denied environments (e.g., space and underwater exploration [1], search and rescue missions [2], and surveillance [3]), an alternative approach for accurate multi-robot pose (i.e., position and orientation) determination is Cooperative Localization (CL) [4]. In CL, instead of localizing independently, groups of communicating robots use their relative measurements (e.g., distance, bearing, and orientation) to jointly estimate their poses, resulting in increased accuracy for the entire team.…”

“…Various approaches that address this issue of resource-constrained CL have been proposed in the literature. For instance, in some cases robots select and transmit a subset of their real-valued 1 (analog) measurements depending on the communication bandwidth availability [7], [8]. However, in this paper we focus on CL under severe communication constraints where each robot can transmit only a single bit per real-valued measurement.…”