We present a closed-loop multi-arm motion planner that is scalable and flexible with team size. Traditional multi-arm robotic systems have relied on centralized motion planners, whose run times often scale exponentially with team size, and thus, fail to handle dynamic environments with open-loop control. In this paper, we tackle this problem with multi-agent reinforcement learning, where a shared policy network is trained to control each individual robot arm to reach its target end-effector pose given observations of its workspace state and target end-effector pose. The policy is trained using Soft Actor-Critic with expert demonstrations from a sampling-based motion planning algorithm (i.e., BiRRT). By leveraging classical planning algorithms, we can improve the learning efficiency of the reinforcement learning algorithm while retaining the fast inference time of neural networks. The resulting policy scales sub-linearly and can be deployed on multi-arm systems with variable team sizes. Thanks to the closed-loop and decentralized formulation, our approach generalizes to 5-10 multiarm systems and dynamic moving targets (>90% success rate for a 10-arm system), despite being trained on only 1-4 arm planning tasks with static targets.
more »
« less
This content will become publicly available on November 7, 2024
End-to-end decentralized formation control using a graph neural network-based learning method
Multi-robot cooperative control has been extensively studied using model-based distributed control methods. However, such control methods rely on sensing and perception modules in a sequential pipeline design, and the separation of perception and controls may cause processing latencies and compounding errors that affect control performance. End-to-end learning overcomes this limitation by implementing direct learning from onboard sensing data, with control commands output to the robots. Challenges exist in end-to-end learning for multi-robot cooperative control, and previous results are not scalable. We propose in this article a novel decentralized cooperative control method for multi-robot formations using deep neural networks, in which inter-robot communication is modeled by a graph neural network (GNN). Our method takes LiDAR sensor data as input, and the control policy is learned from demonstrations that are provided by an expert controller for decentralized formation control. Although it is trained with a fixed number of robots, the learned control policy is scalable. Evaluation in a robot simulator demonstrates the triangular formation behavior of multi-robot teams of different sizes under the learned control policy.
more »
« less
- Award ID(s):
- 1838799
- NSF-PAR ID:
- 10481990
- Publisher / Repository:
- Frontiers
- Date Published:
- Journal Name:
- Frontiers in Robotics and AI
- Volume:
- 10
- ISSN:
- 2296-9144
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We present an incremental scalable motion planning algorithm for finding maximally informative trajectories for decentralized mobile robots. These robots are deployed to observe an unknown spatial field, where the informativeness of observations is specified as a density function. Existing works that are typically restricted to discrete domains and synchronous planning often scale poorly depending on the size of the problem. Our goal is to design a distributed control law in continuous domains and an asynchronous communication strategy to guide a team of cooperative robots to visit the most informative locations within a limited mission duration. Our proposed Asynchronous Information Gathering with Bayesian Optimization (AsyncIGBO) algorithm extends ideas from asynchronous Bayesian Optimization (BO) to efficiently sample from a density function. It then combines them with decentralized reactive motion planning techniques to achieve efficient multi-robot information gathering activities. We provide a theoretical justification for our algorithm by deriving an asymptotic no-regret analysis with respect to a known spatial field. Our proposed algorithm is extensively validated through simulation and real-world experiment results with multiple robots.more » « less
-
Intelligent robots frequently need to explore the objects in their working environments. Modern sensors have enabled robots to learn object properties via perception of multiple modalities. However, object exploration in the real world poses a challenging trade-off between information gains and exploration action costs. Mixed observability Markov decision process (MOMDP) is a framework for planning under uncertainty, while accounting for both fully and partially observable components of the state. Robot perception frequently has to face such mixed observability. This work enables a robot equipped with an arm to dynamically construct query-oriented MOMDPs for multi-modal predicate identification (MPI) of objects. The robot's behavioral policy is learned from two datasets collected using real robots. Our approach enables a robot to explore object properties in a way that is significantly faster while improving accuracies in comparison to existing methods that rely on hand-coded exploration strategies.more » « less
-
In this paper, we present a decentralized control approach based on a Nonlinear Model Predictive Control (NMPC) method that employs barrier certificates for safe navigation of multiple nonholonomic wheeled mobile robots in unknown environments with static and/or dynamic obstacles. This method incorporates a Learned Barrier Function (LBF) into the NMPC design in order to guarantee safe robot navigation, i.e., prevent robot collisions with other robots and the obstacles. We refer to our proposed control approach as NMPC-LBF. Since each robot does not have a priori knowledge about the obstacles and other robots, we use a Deep Neural Network (DeepNN) running in real-time on each robot to learn the Barrier Function (BF) only from the robot's LiDAR and odometry measurements. The DeepNN is trained to learn the BF that separates safe and unsafe regions. We implemented our proposed method on simulated and actual Turtlebot3 Burger robot(s) in different scenarios. The implementation results show the effectiveness of the NMPC-LBF method at ensuring safe navigation of the robots.more » « less
-
more » « less
Abstract Trajectory planning for multiple robots in shared environments is a challenging problem especially when there is limited communication available or no central entity. In this article, we present Real-time planning using Linear Spatial Separations, or RLSS: a real-time decentralized trajectory planning algorithm for cooperative multi-robot teams in static environments. The algorithm requires relatively few robot capabilities, namely sensing the positions of robots and obstacles without higher-order derivatives and the ability of distinguishing robots from obstacles. There is no communication requirement and the robots’ dynamic limits are taken into account. RLSS generates and solves convex quadratic optimization problems that are kinematically feasible and guarantees collision avoidance if the resulting problems are feasible. We demonstrate the algorithm’s performance in real-time in simulations and on physical robots. We compare RLSS to two state-of-the-art planners and show empirically that RLSS does avoid deadlocks and collisions in forest-like and maze-like environments, significantly improving prior work, which result in collisions and deadlocks in such environments.
