---
title: Average Displacement Error (ADE) Explained
url: https://www.emergentmind.com/topics/average-displacement-error-ade
type: topic
---

# Average Displacement Error (ADE) Explained

Average Displacement Error (ADE) is a foundational quantitative metric in trajectory prediction, pedestrian and vehicle forecasting, autonomous driving, safe navigation in GPS-denied environments, and multi-agent interactive systems. It provides a scalar measure of mean positional divergence between a model's predicted path and the true trajectory, assessed over an entire prediction horizon. ADE is ubiquitous in the literature as a primary gauge for model fidelity, yet various works have illuminated critical conceptual and practical limitations, particularly in multi-agent and safety-critical applications.

## 1. Mathematical Formulation and Computation

ADE quantifies average per-step spatial error between predicted and ground-truth trajectories. In its general form, for a trajectory of length $T$, the ADE is:

$$
\mathrm{ADE} = \frac{1}{T} \sum_{t=1}^T \| \hat{\mathbf{p}}_{t} - \mathbf{p}_{t} \|_2
$$

where $\hat{\mathbf{p}}_{t} \in \mathbb{R}^2$ is the predicted position at time $t$, $\mathbf{p}_{t}$ is the ground-truth position, and $\|\cdot\|_2$ is the Euclidean norm [2309.00331][2510.10086][2306.15136][2404.11181][2605.03491][2505.01956][2508.06544][2203.03057].

Extension to multi-agent and multi-modal settings is standard. For $N$ agents:

$$
\mathrm{ADE}_{multi} = \frac{1}{N} \sum_{i=1}^N \frac{1}{T} \sum_{t=1}^{T} \| \hat{\mathbf{p}}_{i,t} - \mathbf{p}_{i,t} \|_2
$$

In probabilistic models, ADE may be computed for each stochastic sample and then further aggregated using a minimum ("Best-of-N") to account for diverse plausible futures [2203.03057][2508.06544].

## 2. Stepwise Evaluation and Workflow

The canonical ADE computation pipeline encompasses:

- **Data Preparation**: Extract historic and future positions for each agent from dataset (e.g., ETH/UCY, SinD, nuScenes) [2309.00331][2404.11181][2510.10086].
- **Prediction Generation**: Model (LSTM, Transformer, GAN, etc.) outputs a sequence $\{ \hat{\mathbf{p}}_t \}_{t=1}^T$ of predicted (x, y) positions [2309.00331][2605.03491].
- **Error Measurement**: For each time step $t$, compute $\| \hat{\mathbf{p}}_t - \mathbf{p}_t \|_2$.
- **Temporal Averaging**: Compute per-trajectory mean over $T$ steps.
- **Dataset-Level Aggregation**: Average ADEs over all trajectories, agents, or test cases.
- **Special Protocols for Multi-Modal Models**: For each agent, assign the prediction sample attaining minimum ADE (“minJointADE,” "BoN-ADE") for fair comparison [2508.06544][2203.03057].
- **Unit Convention**: All distances reported in meters in bird’s-eye or ego-centric frames.

## 3. Reported ADE Values Across Domains

Empirical ADE figures vary widely across domains, datasets, and prediction horizons:

| Application / Dataset         | ADE (Lower is Better)                      | Reference                      |
|------------------------------|---------------------------------------------|--------------------------------|
| Pedestrian (ETH, UCY)        | 1.2586–3.6030 m, 6.2% lower vs baseline     | [2309.00331]                   |
| Multi-vehicle (SinD, KI-GAN) | 0.05 m (6 s), 0.11 m (9 s)                  | [2404.11181]                   |
| Autonomous Driving           | <0.08 m (nominal), 3–4 m under PGD attack   | [2605.03491]                   |
| Digital Twin Work Zones      | 0.1327 m (minJointADE, HPNet model)         | [2508.06544]                   |
| Safe Navigation (real-imit.) | 0.2393 m (LanBLoc-BMM-EKF)                  | [2505.01956]                   |

Low ADE values (sub-meter) signify highly accurate predictions, while scenarios with adversarial inputs yield dramatic increases, highlighting architectural brittleness [2605.03491].

## 4. Comparison with Related Metrics: FDE and Scenario-Based Measures

ADE is typically paired with Final Displacement Error (FDE):

$$
\mathrm{FDE} = \| \hat{\mathbf{p}}_{T} - \mathbf{p}_{T} \|_2
$$

ADE provides a global, path-wide accuracy assessment, while FDE isolates endpoint precision—critical for downstream planning or collision avoidance. In multi-modal evaluations (e.g., GANs, variational predictors), minADE and minFDE are standard, reporting the error of the best mode among $K$ samples [2203.03057][2404.11181][2508.06544][2510.10086].

Extensions to scenario-driven evaluations and alternative risk-weighted metrics (e.g., Average Weighted Risk Score, AWRS [2505.01956]; Average Mahalanobis Distance, AMD [2203.03057]) have emerged to capture safety-critical and uncertainty-aware phenomena beyond displacement-only measures.

## 5. Strengths and Limitations

### Strengths

- **Intuitive:** Directly quantifies mean trajectory error in interpretable spatial units (meters).
- **Holistic:** Aggregates error over the entire forecast, exposing accumulated deviations and the model’s handling of dynamic variations [2309.00331][2306.15136].
- **Broad Applicability:** Usable for single- and multi-agent, deterministic and generative models, across diverse domains.

### Limitations

- **Uniform Step Weighting:** All time steps contribute equally, which can mask large endpoint errors (motivation for FDE) or critical mispredictions near obstacles [2505.01956][2510.10086].
- **Blind to Uncertainty:** Especially in "Best-of-N" formulations, ADE disregards variance and distributional spread, potentially overstating accuracy when only a single mode or sample nears the ground truth [2203.03057].
- **Context-Oblivious:** Fails to distinguish errors occurring in high-risk or scenario-dependent regions (e.g., intersections, merges, curved scenarios); scenario-specific failures may be hidden in aggregate scores [2510.10086].
- **Non-informative for Closed-Loop Safety:** Static, dataset-based ADE demonstrates poor correlation with real-world driving safety or closed-loop control efficacy, due to the dynamics gap (mismatch between open-loop evaluation and closed-loop performance) [2306.15136].

## 6. Identified Biases and Evaluation Controversies

Recent works have challenged ADE as a sole performance indicator:

- **Distributional Bias in BoN-ADE:** Selecting only the minimum error over sampled trajectories renders ADE insensitive to distributional drift or misspecification—entire sample clouds may be misaligned or excessively dispersed despite reporting low ADE for a lucky sample [2203.03057]. Average Mahalanobis Distance (AMD) and Average Maximum Eigenvalue (AMV) have been suggested as alternatives to measure centroidal accuracy and predictive spread, respectively.
- **Unsafe or Blind Regions:** Models can achieve competitive ADEs yet fail in semantically critical regions such as unstructured intersections or map-free areas. Scenario-aware decomposition (by semantic context, agent density, road geometry) has been proposed to expose such vulnerabilities [2510.10086].
- **Dynamics Gap:** ADE on static datasets does not transfer to deployed performance in interactive environments, as the predictor affects the agent’s future, altering the evolution of surrounding traffic or pedestrians [2306.15136]. The introduction of "Dynamic ADE," i.e., ADE in closed-loop simulation or real-time settings, addresses this gap, showing significantly improved correlation to downstream driving quality.

## 7. Domain-Specific Usage Patterns and Extensions

- **Autonomous Driving:** ADE is ubiquitous in reports of predictive fidelity for planners, trajectory predictors, and imitation learners [2306.15136][2605.03491]. Robustness assessment under adversarial attack further utilizes ADE as a stability indicator.
- **Pedestrian Motion and Social Forecasting:** Integral to benchmarks on ETH/UCY, Social-LSTM, and attention-based architectures; multiclass, multimodal, and attention-weighted models consistently report ADE as a principal metric [2309.00331][2203.03057].
- **Safety and Risk-Aware Navigation:** While ADE conveys geometric error, its limitations for risk and hazard awareness have driven the adoption of complementary statistics: risk-aware scores (AWRS), joint ADE (minJointADE), and scenario-filtered metrics [2505.01956][2508.06544][2510.10086].
- **Digital Twin and Multi-Sensor Systems:** High-fidelity simulation platforms and infrastructure-based sensing enable improvements in ADE through sensor fusion and map constraints [2508.06544].

## References

- [2309.00331] Human trajectory prediction using LSTM with Attention mechanism
- [2203.03057] Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimation
- [2510.10086] Beyond ADE and FDE: A Comprehensive Evaluation Framework for Safety-Critical Prediction in Multi-Agent Autonomous Driving Scenarios
- [2306.15136] What Truly Matters in Trajectory Prediction for Autonomous Driving?
- [2605.03491] Real-Time Evaluation of Autonomous Systems under Adversarial Attacks
- [2505.01956] SafeNav: Safe Path Navigation using Landmark Based Localization in a GPS-denied Environment
- [2404.11181] KI-GAN: Knowledge-Informed Generative Adversarial Networks for Enhanced Multi-Vehicle Trajectory Forecasting at Signalized Intersections
- [2508.06544] Historical Prediction Attention Mechanism based Trajectory Forecasting for Proactive Work Zone Safety in a Digital Twin Environment

Source: https://www.emergentmind.com/topics/average-displacement-error-ade