Fleet-Level Battery-Health-Aware Scheduling for Autonomous Mobile Robots

Jiachen Li; Shihao Li; Jian Chu; Wei Li; Dongmei Chen

cs.ROMar 24, 2026

Fleet-Level Battery-Health-Aware Scheduling for Autonomous Mobile Robots

Authors: Jiachen Li, Shihao Li, Jian Chu, Wei Li, Dongmei Chen

Organizations: University of Texas at Austin, Austin, TX 78712 USA

Abstract

Autonomous mobile robot fleets must coordinate task allocation and charging under limited shared resources, yet most battery aware planning methods address only a single robot. This paper extends degradation cost aware task planning to a multi robot setting by jointly optimizing task assignment, service sequencing, optional charging decisions, charging mode selection, and charger access while balancing degradation across the fleet. The formulation relies on reduced form degradation proxies grounded in the empirical battery aging literature, capturing both charging mode dependent wear and idle state of charge dependent aging; the bilinear idle aging term is linearized through a disaggregated piecewise McCormick formulation. Tight big M values derived from instance data strengthen the LP relaxation. To manage scalability, we propose a hierarchical matheuristic in which a fleet level master problem coordinates assignments, routes, and charger usage, while robot level subproblems whose integer part decomposes into trivially small independent partition selection problems compute route conditioned degradation schedules. Systematic experiments compare the proposed method against three baselines: a rule based nearest available dispatcher, an energy aware formulation that enforces battery feasibility without modeling degradation, and a charger unaware formulation that accounts for degradation but ignores shared charger capacity limits.

Figures & tables

Nomenclature
Sets and indices
$\mathcal{R}$	Set of robots, indexed by $r$
$\mathcal{K}$	Set of tasks, indexed by $k$
$\mathcal{M}$	Set of chargers, indexed by $m$
$\mathcal{L}_{r}$	Admissible charging modes for robot $r$ , indexed by $\ell$
$\mathcal{V}^{-},\mathcal{V}^{+}$	Source/sink augmented node sets

Table 1

Figure 1: Direct and charging transitions with shared-charger non-overlap coupling.

Figure 2: Hierarchical matheuristic workflow.

Symbol	Value	Unit
$S_{r}^{\max}$ / $S_{r}^{\min}$ / $S_{r}^{0}$	1.0 / 0.1 / 0.8	frac. cap.
$c_{r,\text{std}}$ / $c_{r,\text{fast}}$	0.01 / 0.025	frac./min
$\alpha_{r,\text{std}}$ / $\alpha_{r,\text{fast}}$	5e-5 / 1.5e-4	frac. loss/min
$\beta_{r}$	3e-5	$\tfrac{\text{frac.\ loss}}{\text{SOC}\cdot\text{min}}$

Table 1: Baseline battery and degradation parameters.

Method	$\sum A_{r}$	$A^{\max}$	Tard.	Solve (s)
Rule-based	0.214	0.102	462.7	0.7
Energy-aware	0.137	0.079	171.4	32.1
Chgr-unaware	0.118	0.084	149.6	40.6
Monolithic	0.093	0.057	119.2	132.2
Proposed	0.098	0.060	124.5	24.8

Table 2: Illustrative comparison (

|\mathcal{R}|{=}4

|\mathcal{K}|{=}40

|\mathcal{M}|{=}2

Figure 3: Degradation–tardiness Pareto front as $\mu$ varies.

$R$	$K$	$M$	Method	Obj.	Solve (s)
2	20	1	Rule-based	52.3	0.2
			Energy-aware	44.1	0.7
			Chgr-unaware	43.5	1.0
			Monolithic	41.7	1.8
			Proposed	42.4	0.6
4	40	2	Rule-based	168.3	0.7

Table 3: Scalability comparison across all methods.

Figure 4: Warehouse trajectories (3 robots, 30 tasks, 2 chargers).

Figure 5: SOC traces; upward jumps indicate charging events.

Multi-Robot Task Allocation

Multi-robot task allocation assigns work across robot teams while balancing capabilities, costs, timing, and coordination constraints.

See all 112 papers

Deep Reinforcement Learning for Dynamic Battery Management of Autonomous Order Pickers
Jul 6, 2026Taniya Shaji, Abhay Sobhanan, Christof DefrynRL for Robotics Mobile Robotics
Indian Institute of Management Bangalore, Bannerghatta Road, Bengaluru 560076, Karnataka, India · University of Antwerp, Prinsstraat 13, Antwerp 2000, Belgium
Auction-Based Task Allocation with Energy-Conscientious Trajectory Optimization for AMR Fleets
Mar 23, 2026Jiachen Li, Soovadeep Bakshi, Jian Chu +2Multi-Robot Task Allocation Multi-Agent Resource Allocation
All authors are with the Department of Mechanical Engineering, The University of Texas at Austin, Austin, TX 78712, USA.
Atomic Proximal Policy Optimization for Electric Robo-Taxi Dispatch and Charger Allocation
Feb 19, 2025Jim Dai, Manxi Wu, Zhanhao ZhangProximal Policy Optimization Electric Vehicle Charging
Operations Research and Information Engineering, Cornell University · Department of Civil and Environmental Engineering, University of California, Berkeley

Jul 6, 2026J/K move · Enter open · S save

Deep Reinforcement Learning for Dynamic Battery Management of Autonomous Order Pickers

Taniya Shaji, Abhay Sobhanan, Christof Defryn

Indian Institute of Management Bangalore, Bannerghatta Road, Bengaluru 560076, Karnataka, India · University of Antwerp, Prinsstraat 13, Antwerp 2000, Belgium

RL for Robotics Mobile Robotics Multi-Robot Coordination Warehouse Automation

Open paper AskPDF arXiv

Battery charging of Autonomous Mobile Robots (AMRs) in warehouses is a critical operational challenge that heavily impacts both order processing times and throughput. In this study, we address the dynamic AMR charging problem under stochastic order arrivals, where robots must learn optimal charging decisions. Traditional fixed-rule heuristics often prove suboptimal in dynamic environments and fail to account for multi-AMR coordination, leading to severe resource inefficiencies. To overcome these limitations, we propose a Proximal Policy Optimization (PPO)-based Deep Reinforcement Learning (DRL) framework designed for multi-block warehouses with fixed charging stations. Our model dynamically learns two key decisions: charging station selection and optimal charging duration, explicitly accounting for anticipated queuing times at the stations. Extensive numerical experiments benchmark the proposed model against state-of-the-art DRL and traditional heuristic approaches. Results demonstrate that our PPO framework increases order-completion rates by up to 6% compared to the strongest baseline, while significantly reducing the total time dedicated to recharging operations. Furthermore, we validate the model's robustness across diverse warehouse configurations and stochastic arrival rates. Finally, we interpret the learned DRL policy, offering valuable operational insights into its superiority over standard benchmarks.

Abstract

Multi-Robot Task Allocation

Explore similar work

Deep Reinforcement Learning for Dynamic Battery Management of Autonomous Order Pickers

Auction-Based Task Allocation with Energy-Conscientious Trajectory Optimization for AMR Fleets

Atomic Proximal Policy Optimization for Electric Robo-Taxi Dispatch and Charger Allocation