Confidence-aware motion prediction for real-time collision avoidance1
| Autor: | Steven Wang, David Fridovich-Keil, Sylvia L. Herbert, Claire J. Tomlin, Jaime F. Fisac, Andrea Bajcsy, Anca D. Dragan |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
0209 industrial biotechnology
Thesaurus (information retrieval) business.industry Computer science Applied Mathematics Mechanical Engineering 05 social sciences 02 engineering and technology Collision 020901 industrial engineering & automation Artificial Intelligence Modeling and Simulation Motion prediction 0501 psychology and cognitive sciences Motion planning Artificial intelligence Robot motion planning Electrical and Electronic Engineering Robust control business 050107 human factors Software |
| Zdroj: | The International Journal of Robotics Research. 39:250-265 |
| ISSN: | 1741-3176 0278-3649 |
| Popis: | One of the most difficult challenges in robot motion planning is to account for the behavior of other moving agents, such as humans. Commonly, practitioners employ predictive models to reason about where other agents are going to move. Though there has been much recent work in building predictive models, no model is ever perfect: an agent can always move unexpectedly, in a way that is not predicted or not assigned sufficient probability. In such cases, the robot may plan trajectories that appear safe but, in fact, lead to collision. Rather than trust a model’s predictions blindly, we propose that the robot should use the model’s current predictive accuracy to inform the degree of confidence in its future predictions. This model confidence inference allows us to generate probabilistic motion predictions that exploit modeled structure when the structure successfully explains human motion, and degrade gracefully whenever the human moves unexpectedly. We accomplish this by maintaining a Bayesian belief over a single parameter that governs the variance of our human motion model. We couple this prediction algorithm with a recently proposed robust motion planner and controller to guide the construction of robot trajectories that are, to a good approximation, collision-free with a high, user-specified probability. We provide extensive analysis of the combined approach and its overall safety properties by establishing a connection to reachability analysis, and conclude with a hardware demonstration in which a small quadcopter operates safely in the same space as a human pedestrian. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|