DynoJEPP: Joint Estimation, Prediction and Planning in Dynamic Environments

2026-05-12

AI Summary

This work addresses a critical issue in traditional joint estimation, prediction, and planning frameworks, where feedback from prediction and planning modules adversely influences state estimation, leading to biased estimates and unsafe behaviors. To resolve this, the authors propose DynoJEPP—a factor graph–based joint optimization framework that explicitly constrains the direction of information flow through directed factors, thereby effectively blocking backward interference from prediction and planning into state estimation. The approach is further extended to multi-agent settings as Cooperative DynoJEPP, enabling joint modeling of collaborative agents’ behaviors. Experimental results demonstrate that directed factors are essential for safe navigation: their absence results in frequent collisions across most scenarios, whereas their inclusion significantly enhances system safety and robustness.

Abstract

DynoJEPP is a factor-graph-based framework that jointly formulates and simultaneously optimizes estimation, prediction, and planning in dynamic environments. In conventional factor-graph-based approaches that jointly formulate estimation, prediction, and planning, information from prediction and planning feeds back into state estimation, yielding corrupted estimates, undesired behaviors, and unsafe plans. To address this, DynoJEPP introduces a novel directed factor that enforces directional information flow within the factor graph, preventing prediction and planning from corrupting state estimation. We evaluate the impact of directed factors on inter-module interactions during navigation in both static and dynamic environments. Our results demonstrate that these factors are critical for safe operation, as without them, the robot collides in the majority of experiments. Building on this, we further introduce Cooperative DynoJEPP, which enables the ego robot to incorporate cooperative object behavior into its prediction and trajectory planning.

Problem

• joint estimation
• prediction
• planning
• dynamic environments
• factor graph

Innovation

• directed factor
• joint estimation-prediction-planning
• factor graph
• dynamic environments
• cooperative planning