On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous Driving

• URL: http://arxiv.org/abs/2403.01238v2
• Date: Mon, 15 Apr 2024 07:12:20 GMT
• Title: On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous Driving
• Authors: Kaituo Feng, Changsheng Li, Dongchun Ren, Ye Yuan, Guoren Wang,
• Abstract summary: End-to-end motion planning models equipped with deep neural networks have shown great potential for enabling full autonomous driving. The oversized neural networks render them impractical for deployment on resource-constrained systems, which unavoidably requires more computational time and resources during reference. We propose PlanKD, the first knowledge distillation framework tailored for compressing end-to-end motion planners.
• Score: 38.35997586629021
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: End-to-end motion planning models equipped with deep neural networks have shown great potential for enabling full autonomous driving. However, the oversized neural networks render them impractical for deployment on resource-constrained systems, which unavoidably requires more computational time and resources during reference.To handle this, knowledge distillation offers a promising approach that compresses models by enabling a smaller student model to learn from a larger teacher model. Nevertheless, how to apply knowledge distillation to compress motion planners has not been explored so far. In this paper, we propose PlanKD, the first knowledge distillation framework tailored for compressing end-to-end motion planners. First, considering that driving scenes are inherently complex, often containing planning-irrelevant or even noisy information, transferring such information is not beneficial for the student planner. Thus, we design an information bottleneck based strategy to only distill planning-relevant information, rather than transfer all information indiscriminately. Second, different waypoints in an output planned trajectory may hold varying degrees of importance for motion planning, where a slight deviation in certain crucial waypoints might lead to a collision. Therefore, we devise a safety-aware waypoint-attentive distillation module that assigns adaptive weights to different waypoints based on the importance, to encourage the student to accurately mimic more crucial waypoints, thereby improving overall safety. Experiments demonstrate that our PlanKD can boost the performance of smaller planners by a large margin, and significantly reduce their reference time.

Related papers

• DiFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient End-to-End Self-Driving [55.53171248839489]
  We propose an ego-centric fully sparse paradigm, named DiFSD, for end-to-end self-driving. Specifically, DiFSD mainly consists of sparse perception, hierarchical interaction and iterative motion planner. Experiments conducted on nuScenes and Bench2Drive datasets demonstrate the superior planning performance and great efficiency of DiFSD.
  arXiv  Detail & Related papers  (2024-09-15T15:55:24Z)
• Potential Based Diffusion Motion Planning [73.593988351275]
  We propose a new approach towards learning potential based motion planning. We train a neural network to capture and learn an easily optimizable potentials over motion planning trajectories. We demonstrate its inherent composability, enabling us to generalize to a multitude of different motion constraints.
  arXiv  Detail & Related papers  (2024-07-08T17:48:39Z)
• Interpretable and Flexible Target-Conditioned Neural Planners For Autonomous Vehicles [22.396215670672852]
  Prior work only learns to estimate a single planning trajectory, while there may be multiple acceptable plans in real-world scenarios. We propose an interpretable neural planner to regress a heatmap, which effectively represents multiple potential goals in the bird's-eye view of an autonomous vehicle. Our systematic evaluation on the Lyft Open dataset shows that our model achieves a safer and more flexible driving performance than prior works.
  arXiv  Detail & Related papers  (2023-09-23T22:13:03Z)
• Interpretable Motion Planner for Urban Driving via Hierarchical Imitation Learning [5.280496662905411]
  We introduce a hierarchical planning architecture including a high-level grid-based behavior planner and a low-level trajectory planner. As the high-level planner is responsible for finding a consistent route, the low-level planner generates a feasible trajectory. We evaluate our method both in closed-loop simulation and real world driving, and demonstrate the neural network planner has outstanding performance.
  arXiv  Detail & Related papers  (2023-03-24T13:18:40Z)
• PlanT: Explainable Planning Transformers via Object-Level Representations [64.93938686101309]
  PlanT is a novel approach for planning in the context of self-driving. PlanT is based on imitation learning with a compact object-level input representation. Our results indicate that PlanT can focus on the most relevant object in the scene, even when this object is geometrically distant.
  arXiv  Detail & Related papers  (2022-10-25T17:59:46Z)
• Differentiable Spatial Planning using Transformers [87.90709874369192]
  We propose Spatial Planning Transformers (SPT), which given an obstacle map learns to generate actions by planning over long-range spatial dependencies. In the setting where the ground truth map is not known to the agent, we leverage pre-trained SPTs in an end-to-end framework. SPTs outperform prior state-of-the-art differentiable planners across all the setups for both manipulation and navigation tasks.
  arXiv  Detail & Related papers  (2021-12-02T06:48:16Z)
• Trajectory Planning for Autonomous Vehicles Using Hierarchical Reinforcement Learning [21.500697097095408]
  Planning safe trajectories under uncertain and dynamic conditions makes the autonomous driving problem significantly complex. Current sampling-based methods such as Rapidly Exploring Random Trees (RRTs) are not ideal for this problem because of the high computational cost. We propose a Hierarchical Reinforcement Learning structure combined with a Proportional-Integral-Derivative (PID) controller for trajectory planning.
  arXiv  Detail & Related papers  (2020-11-09T20:49:54Z)
• The Importance of Prior Knowledge in Precise Multimodal Prediction [71.74884391209955]
  Roads have well defined geometries, topologies, and traffic rules. In this paper we propose to incorporate structured priors as a loss function. We demonstrate the effectiveness of our approach on real-world self-driving datasets.
  arXiv  Detail & Related papers  (2020-06-04T03:56:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.