Learning Sidewalk Autopilot from Multi-Scale Imitation with Corrective Behavior Expansion

• URL: http://arxiv.org/abs/2603.22527v1
• Date: Mon, 23 Mar 2026 19:41:21 GMT
• Title: Learning Sidewalk Autopilot from Multi-Scale Imitation with Corrective Behavior Expansion
• Abstract summary: Sidewalk micromobility is a promising solution for last-mile transportation.<n>Current learning-based control methods struggle in complex urban environments.<n>We propose a framework that advances imitation learning through corrective behavior expansion and multi-scale imitation learning.
• Score: 49.12280766257823
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sidewalk micromobility is a promising solution for last-mile transportation, but current learning-based control methods struggle in complex urban environments. Imitation learning (IL) learns policies from human demonstrations, yet its reliance on fixed offline data often leads to compounding errors, limited robustness, and poor generalization. To address these challenges, we propose a framework that advances IL through corrective behavior expansion and multi-scale imitation learning. On the data side, we augment teleoperation datasets with diverse corrective behaviors and sensor augmentations to enable the policy to learn to recover from its own mistakes. On the model side, we introduce a multi-scale IL architecture that captures both short-horizon interactive behaviors and long-horizon goal-directed intentions via horizon-based trajectory clustering and hierarchical supervision. Real-world experiments show that our approach significantly improves robustness and generalization in diverse sidewalk scenarios.

Related papers

• Hierarchical Federated Unlearning for Large Language Models [5.406594712642111]
  Large Language Models (LLMs) are increasingly integrated into real-world applications, raising concerns about privacy, security and the need to remove undesirable knowledge.<n>We propose a federated unlearning approach for LLMs that is scalable and privacy preserving.<n>Our method decouples unlearning and retention via task-specific adapter learning and employs a hierarchical merging strategy to mitigate conflicting objectives.
  arXiv  Detail & Related papers  (2025-10-19T04:24:51Z)
• Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling [26.71028572181775]
  Modeling interactive driving behaviors in complex scenarios remains a fundamental challenge for autonomous driving planning.<n>We propose Flow Planner, which tackles these problems through coordinated innovations in data modeling, model architecture, and learning scheme.<n>Flow Planner achieves state-of-the-art performance among learning-based approaches while effectively modeling interactive behaviors in complex driving scenarios.
  arXiv  Detail & Related papers  (2025-10-13T07:25:13Z)
• Curriculum Imitation Learning of Distributed Multi-Robot Policies [5.376095069606724]
  Learning control policies for multi-robot systems are a major challenge due to long-term coordination and the difficulty of obtaining realistic training data.<n>We propose a curriculum strategy that gradually increases the length of expert trajectories during training.<n>We also introduce a method to approximate the egocentric perception of each robot using only third-person global state demonstrations.
  arXiv  Detail & Related papers  (2025-09-29T17:31:48Z)
• TrajBooster: Boosting Humanoid Whole-Body Manipulation via Trajectory-Centric Learning [79.59753528758361]
  We present TrajBooster, a cross-embodiment framework that leverages abundant wheeled-humanoid data to boost bipedal VLA.<n>Our key idea is to use end-effector trajectories as a morphology-agnostic interface.<n>Results show that TrajBooster allows existing wheeled-humanoid data to efficiently strengthen bipedal humanoid VLA performance.
  arXiv  Detail & Related papers  (2025-09-15T12:25:39Z)
• Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting [70.83781268763215]
  Vision-language models (VLMs) have achieved impressive performance across diverse multimodal tasks by leveraging large-scale pre-training.<n>VLMs face unique challenges such as cross-modal feature drift, parameter interference due to shared architectures, and zero-shot capability erosion.<n>This survey aims to serve as a comprehensive and diagnostic reference for researchers developing lifelong vision-language systems.
  arXiv  Detail & Related papers  (2025-08-06T09:03:10Z)
• From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning [59.88543114325153]
  We introduce the Seeing-to-Experiencing framework to scale the capability of navigation foundation models with reinforcement learning.<n>S2E combines the strengths of pre-training on videos and post-training through RL.<n>We establish a comprehensive end-to-end evaluation benchmark, NavBench-GS, built on photorealistic 3DGS reconstructions of real-world scenes.
  arXiv  Detail & Related papers  (2025-07-29T17:26:10Z)
• Collaborative Imputation of Urban Time Series through Cross-city Meta-learning [54.438991949772145]
  We propose a novel collaborative imputation paradigm leveraging meta-learned implicit neural representations (INRs)<n>We then introduce a cross-city collaborative learning scheme through model-agnostic meta learning.<n>Experiments on a diverse urban dataset from 20 global cities demonstrate our model's superior imputation performance and generalizability.
  arXiv  Detail & Related papers  (2025-01-20T07:12:40Z)
• Open-World Reinforcement Learning over Long Short-Term Imagination [91.28998327423295]
  Training visual reinforcement learning agents in a high-dimensional open world presents significant challenges.<n>We present LS-Imagine, which extends the imagination horizon within a limited number of state transition steps.<n>Our method demonstrates significant improvements over state-of-the-art techniques in MineDojo.
  arXiv  Detail & Related papers  (2024-10-04T17:17:30Z)
• Sequential Neural Barriers for Scalable Dynamic Obstacle Avoidance [7.375976854181687]
  We propose a novel method for compositional learning of Sequential Neural Control Barrier models (SNCBFs) Our approach exploits an important observation: the spatial interaction patterns of multiple dynamic obstacles can be decomposed and predicted through temporal sequences of states for each obstacle. We demonstrate the benefits of the proposed methods in improving dynamic collision avoidance in comparison with existing methods.
  arXiv  Detail & Related papers  (2023-07-06T14:24:17Z)
• Multi-behavior Self-supervised Learning for Recommendation [36.42241501002167]
  We propose a Multi-Behavior Self-Supervised Learning (MBSSL) framework together with an adaptive optimization method. Specifically, we devise a behavior-aware graph neural network incorporating the self-attention mechanism to capture behavior multiplicity and dependencies. Experiments on five real-world datasets demonstrate the consistent improvements obtained by MBSSL over ten state-of-the art (SOTA) baselines.
  arXiv  Detail & Related papers  (2023-05-22T15:57:32Z)
• Visual Adversarial Imitation Learning using Variational Models [60.69745540036375]
  Reward function specification remains a major impediment for learning behaviors through deep reinforcement learning. Visual demonstrations of desired behaviors often presents an easier and more natural way to teach agents. We develop a variational model-based adversarial imitation learning algorithm.
  arXiv  Detail & Related papers  (2021-07-16T00:15:18Z)
• MetaVIM: Meta Variationally Intrinsic Motivated Reinforcement Learning for Decentralized Traffic Signal Control [54.162449208797334]
  Traffic signal control aims to coordinate traffic signals across intersections to improve the traffic efficiency of a district or a city. Deep reinforcement learning (RL) has been applied to traffic signal control recently and demonstrated promising performance where each traffic signal is regarded as an agent. We propose a novel Meta Variationally Intrinsic Motivated (MetaVIM) RL method to learn the decentralized policy for each intersection that considers neighbor information in a latent way.
  arXiv  Detail & Related papers  (2021-01-04T03:06:08Z)

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.