Collective Autonomous Vehicle Routing Needs Social Awareness for Coexistence with Human Drivers

Anastasia Psarou; Mikolaj Rams; Blazej Torbus; Rafal Kucharski

cs.MAOct 9, 2026

Collective Autonomous Vehicle Routing Needs Social Awareness for Coexistence with Human Drivers

Authors: Anastasia Psarou, Mikolaj Rams, Blazej Torbus, Rafal Kucharski

Organizations: Faculty of Mathematics and Computer Science, Jagiellonian University Kraków, Poland

Abstract

Collective Autonomous Vehicle (AV) route choices in real-world traffic networks can create externalities for Human-Driven Vehicles (HDVs), as routes that benefit AVs may increase travel times for other road users. To address this, we introduce a social component, the marginal cost, to the selfish travel time AV reward. Marginal cost captures an AV's impact on other road users by comparing their travel times with those in a counterfactual simulation in which the AV is removed. We study AV route choice in mixed-autonomy traffic settings using Multi-Agent Reinforcement Learning (MARL), where AVs learn routing policies through repeated interactions with the traffic environment. Experiments on the real-world networks of Ingolstadt and Provins show that incorporating marginal cost into the AV reward not only limits the increase in HDV travel times and shortens AV travel times relative to selfish AV routing, but also improves overall system performance. In Ingolstadt, selfish routing of 40% AVs increases the travel times of other vehicles by 1.7%, and this drops to 1.1% when the social reward is included. Interestingly, not only does overall system performance improve, but the AVs are also better off when acting socially.This effect is consistent across tested cities, penetration rates, and replications, yet when the weight of the social component in the reward increases, the system fails to reach the desired performance. For a more scalable approach to social AV routing in mixed-autonomy traffic, we compute the marginal cost only for the AVs whose route choices most affect the traffic system. This reduces the number of counterfactual simulations and achieves similar performance at a significantly lower computational cost. Our results suggest that AV routing should go beyond selfish rewards and, for the benefit of all traffic participants, include a social component in its objective.

Figures & tables

Figure 1: We study AV route choice in traffic environments shared with human drivers. (A) When AVs selfishly minimize their own travel times, their routing decisions can increase HDV travel times. (B) Incorporating our marginal cost into the AV reward allows AVs to account for the impact of their route choices on other road users, mitigating the increase in HDV travel times observed under selfish AV routing while also improving AV travel times on average. However, computing marginal cost requires additional counterfactual simulations for each AV, adding computational cost. (C) To reduce this burden, we introduce selective marginal cost reward shaping, which computes marginal cost rewards only for a subset of the most impactful AVs. This preserves some of the benefits for AVs and HDVs’ travel times while reducing the number of counterfactual simulations.

Figure 2: Traffic networks of Ingolstadt with 1035 agents (a) [ 21 ] , and Provins (b) with 523 agents [ 2 ] .

Figure 3: Average agent relative travel time change, computed as the difference between travel time before AV introduction and travel time during the testing phase, normalized by travel time before AV introduction. Negative values indicates the vehicle is disadvantaged after AV introduction, and a positive indicate the vehicle is better off after AV introduction. Values are averaged across three experimental seed replications, with standard deviations reported in the Supplementary Material.

Figure 4: Change in average AV, and HDV travel times at 40% AV penetration in Ingolstadt at various weights of social component

\beta

in the reward. Negative values indicate shorter travel times compared to the system average.

Figure 5: Mean percentage of AVs choosing routes from respective groups averaged over the 100 days of the testing phase on the Ingolstadt (a) and Provins (b) networks for a 40% AV penetration rate.

Behavior	MC AVs	Counterfactual simulations	HDVs	AVs	AV subgroups	All
$\beta=0.0$
Selfish	–	-	$-1.66\pm 0.19$	$+3.74\pm 0.75$	–	$+0.50\pm 0.41$
$\beta=0.1$
MC	100%	4,140k	$-1.06\pm 0.17$	$+3.79\pm 0.71$	MC: $+3.79\pm 0.71$	$+0.88\pm 0.39$
Selective MC	50%	2,070k	$-1.17\pm 0.18$	$+3.78\pm 0.72$	MC: $+3.51\pm 0.74$ Selfish: $+4.05\pm 0.70$	$+0.81\pm 0.39$
Selective MC	40%	1,660k	$-1.25\pm 0.17$	$+3.78\pm 0.73$	MC: $+3.30\pm 0.75$ Selfish: $+4.10\pm 0.72$	$+0.76\pm 0.38$

Table 1: Selective marginal cost reward shaping, specifically when 40% or 50% of the most impactful AVs are rewarded with the marginal cost, can achieve relative travel-time changes (see Figure 3 ) close to those obtained when all AVs receive the marginal cost reward, while reducing the number of counterfactual simulations. The results are reported for the Ingolstadt traffic network with 40% AV penetration. The AV subgroups column reports the relative travel-time change of selfish AVs (Selfish) and AVs receiving the marginal cost reward (MC). MC denotes marginal cost. Values are reported as mean

\pm

standard deviation across experimental replications.

Figure 6: Empirical cumulative distribution of historical agent impact scores

H_{i}

retrieved from dataset

\mathcal{D}

of 800 thousand joint actions sampled in Ingolstadt. Dashed lines indicate the 50th, 80th, 90th, and 95th percentiles.

Vehicle Routing

Vehicle routing studies how to assign and sequence trips for fleets while meeting capacity, time, energy, and service constraints.

See all 135 papers

Jul 16, 2026

Randomized routing strategies of fleets of CAVs may prove market efficient

In future cities every driver may own a vehicle which could be either independently driven (HDV), or autonomously routed and piloted (CAV). The autonomous operations could be handled by a few competing companies. What is the market structure which would make this market aligned with city goals? In this paper we discuss a variant of the emerging market of collectively routed fleets of CAVs, where revenue for fleet operators is proportional to market share. We provide benchmark scenarios to compare the routing algorithms. We present several routing algorithms and demonstrate that, when the attitudes of human drivers towards CAVs exhibit significant diversity, randomised CAV routing, resulting in unpredictable travel times for HDVs, is more efficient than routing proportional to system optimum/user equilibrium. Based on this, we propose to improve the design of the market by augmenting the market-share objective with mean systemwide travel time in order to limit antisocial randomised strategies of fleet operators and drive the competition towards social welfare oriented cooperation.

Grzegorz Jamróz, Łukasz Gorczyca, Rafał Kucharski

Faculty of Mathematics and Computer Science, Jagiellonian University, Kraków, Poland

Intelligent Transportation Systems Vehicle Routing Autonomous Driving Planning

Ask PDF

Sep 14, 2026

From Learned-Mode AV-Traffic Pairing to Planner Decisions: A Marginal-Preserving Study on Argoverse 2

Joint motion forecasts pair each autonomous-vehicle (AV) future with surrounding traffic, but actor-level metrics do not show whether that structure matters to a planner. We study this question with a marginal-preserving product control that removes AV-traffic pairing among the learned modes while retaining the fixed constant-velocity pair and holding trajectories, actor-level marginals before planner conditioning, candidates, the cost terms and weights, and fallback fixed. The intervention also changes candidate-conditioned concentration. Across twelve runs on 1,400 held-out Argoverse 2 scenarios, the intervention changes 3.0% of route-level offline selections at

τ=4

m. Control-minus-joint recorded-trajectory regret is

-0.026

and

-0.118

at the two training sizes; crossed and seed-

t

intervals span zero. At

τ=1

m, relative costs change in 87.9% of route evaluations and route-level offline selections in 8.1%. Before concentration matching, descriptive outcome estimates favor the control. Most of this gap disappears along an approximate concentration-matching path; the remaining contrasts are

+0.112

and

-0.047

, and both crossed intervals span zero. Actor-level forecast metrics remain identical. Pairing-strength and temperature sweeps show that the decision contrast grows with pairing removal and sharper conditioning. The intervention changes planner decisions even though actor-level metrics remain unchanged. The matching analysis, however, cannot separate any recorded-outcome effect of learned-mode AV-traffic pairing from the accompanying change in conditioned concentration.

Jingyu Wang

Independent Researcher.

Multi-Agent Trajectory Prediction Autonomous Driving Planning

Ask PDF

Jul 27, 2026

Unequal Trips, Unequal Places: Diagnosing and Mitigating Delay Inequity in Autonomous Vehicle Fleet Coordination

City-scale autonomous vehicle fleet coordinators are typically optimized for aggregate travel time, yet fleet averages conceal how delay is distributed across trips and regions. We conduct a distributional audit on three real-city road-network and taxi-demand datasets from Manhattan, Chicago, and San Francisco. The audit reveals pervasive trip-length inequity whose direction depends on the city and coordinator. After accounting for trip length, spatial inequity becomes more pronounced as demand grows and is consistently stronger when trips are grouped by origin rather than destination. These findings motivate SPatially Aware RErouting (SPARE), a budgeted online coordination framework that assigns limited replanning capacity to delayed vehicles and redirects them using recently observed waiting pressure. SPARE provides a per-review decision guarantee and explicitly bounds online route updates. Experiments on all three datasets against six representative baselines show that SPARE delivers the strongest joint efficiency-fairness performance while retaining city-scale scalability. The results demonstrate that bounded congestion-responsive rerouting improves performance and equity without full-fleet replanning.

Nicole Hu, Mingtao Zhang, Haoyang LI +2

School of Hotel and Tourism Management The Hong Kong Polytechnic University Hong Kong SAR, China · Department of Computing The Hong Kong Polytechnic University Hong Kong SAR, China · School of Hotel and Tourism Management & Computing The Hong Kong Polytechnic University Hong Kong SAR, China

Algorithmic Fairness Vehicle Routing Multi-Robot Coordination Autonomous Driving Planning

Ask PDF

Abstract

Vehicle Routing

Explore similar work

Randomized routing strategies of fleets of CAVs may prove market efficient

From Learned-Mode AV-Traffic Pairing to Planner Decisions: A Marginal-Preserving Study on Argoverse 2

Unequal Trips, Unequal Places: Diagnosing and Mitigating Delay Inequity in Autonomous Vehicle Fleet Coordination