Multi-robot grasp planning for sequential assembly operations

Abstract

This paper addresses the problem of finding robot configurations to grasp assembly parts during a sequence of collaborative assembly operations. We formulate the search for such configurations as a constraint satisfaction problem (CSP). Collision constraints in an operation and transfer constraints between operations determine the sets of feasible robot configurations. We show that solving the connected constraint graph with off-the-shelf CSP algorithms can quickly become infeasible even for a few sequential assembly operations. We present an algorithm which, through the assumption of feasible regrasps, divides the CSP into independent smaller problems that can be solved exponentially faster. The algorithm then uses local search techniques to improve this solution by removing a gradually increasing number of regrasps from the plan. The algorithm enables the user to stop the planner anytime and use the current best plan if the cost of removing regrasps from the plan exceeds the cost of executing those regrasps. We present simulation experiments to compare our algorithm's performance to a naive algorithm which directly solves the connected constraint graph. We also present a physical robot system which uses the output of our planner to grasp and bring parts together in assembly configurations.

Task-Specific Sensor Planning for Robotic Assembly Tasks

“…Our work is also related to grasp planners that take into account task constraints [7], [8], [17] and multiple robots [40]. Particularly, the planner we present in Section IV is an extension of the planner from [18]. We build on this literature and extend it to plan simultaneously for multirobot constraints and sensor positioning.…”

“…ASSEMBLY AND SENSOR POSITIONING We now describe the use of task-specific uncertainty estimation within a planner for multi-robot assembly tasks. The planner we used is an extension of [18], which formulates multi-robot planning as a constraint satisfaction problem. The work of [18], however, does not reason about sensing and assumes perfect observability.…”

“…The planner we used is an extension of [18], which formulates multi-robot planning as a constraint satisfaction problem. The work of [18], however, does not reason about sensing and assumes perfect observability. We extend the planning algorithm to simultaneously solve the multi-robot planning and the sensor placement problem, by choosing the feasible plan with the most informative sensor pose.…”

Interactive Leader–Follower Consensus of Multiple Quadrotors Based on Composite Nonlinear Feedback Control

“…Therefore, multi-agent systems have broadly appeared in several applications including multi-vehicle system [2] [3], formation flight of unmanned air vehicles (UAVs) [4] [5] [6], sensor networks [7], self-organization, automated highway systems, and congestion control in communication networks [8].…”

Communication-based and Communication-less approaches for Robust Cooperative Planning in Construction with a Team of UAVs

“…In most of the previous works, the two types of constraints are treated separately: first, a high-level assembly plan is computed considering assembly constraints only. Subsequently, robot actions and movements are planned considering geometric constraints only [9], [10]. This approach implicitly assumes that for any given assembly plan, it is possible to find a set of feasible robot motions.…”