CostNav: A Navigation Benchmark for Cost-Aware Evaluation of Embodied Agents

2025-11-25

AI Summary

Existing navigation benchmarks overemphasize task success rate while neglecting economic feasibility—a critical bottleneck for commercial deployment of autonomous delivery robots. Method: We propose CostNav, the first micro-navigation economic evaluation framework for embodied agents, integrating hardware cost, energy consumption, collision-related maintenance expenses, and delivery revenue into a quantifiable cost–benefit model. Contribution/Results: We empirically reveal a significant decoupling between navigation success rate and economic profitability: under a 43.0% SLA compliance rate, baseline methods incur an average loss of $30.01 per delivery, with 99.7% of costs attributable to collision maintenance and no breakeven point. Leveraging industry-driven modeling and simulation-to-reality mapping, we unify rule-based control, imitation learning, and cost-aware reinforcement learning to establish economic efficiency as a primary optimization objective for navigation algorithm design.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success

Abstract

Existing navigation benchmarks focus on task success metrics while overlooking economic viability -- critical for commercial deployment of autonomous delivery robots. We introduce emph{CostNav}, a extbf{Micro-Navigation Economic Testbed} that evaluates embodied agents through comprehensive cost-revenue analysis aligned with real-world business operations. CostNav models the complete economic lifecycle including hardware, training, energy, maintenance costs, and delivery revenue with service-level agreements, using industry-derived parameters. extbf{To our knowledge, CostNav is the first work to quantitatively expose the gap between navigation research metrics and commercial viability}, revealing that optimizing for task success fundamentally differs from optimizing for economic deployment. Our cost model uses parameters derived from industry data sources (energy rates, delivery service pricing), and we project from a reduced-scale simulation to realistic deliveries. Under this projection, the baseline achieves 43.0% SLA compliance but is emph{not} commercially viable: yielding a loss of $30.009 per run with no finite break-even point, because operating costs are dominated by collision-induced maintenance, which accounts for 99.7% of per-run costs and highlights collision avoidance as a key optimization target. We demonstrate a learning-based on-device navigation baseline and establish a foundation for evaluating rule-based navigation, imitation learning, and cost-aware RL training. CostNav bridges the gap between navigation research and commercial deployment, enabling data-driven decisions about economic trade-offs across navigation paradigms.

Problem

• Existing navigation benchmarks overlook economic viability for commercial robot deployment
• Current navigation metrics differ fundamentally from optimizing for economic deployment success
• Collision-induced maintenance dominates operating costs making baseline systems unprofitable

Innovation

• Introduces CostNav economic testbed for cost-revenue analysis
• Models complete economic lifecycle using industry-derived parameters
• Quantitatively exposes gap between navigation metrics and commercial viability