Abstract:We introduce Large Language Model-Assisted Preference Prediction (LAPP), a novel framework for robot learning that enables efficient, customizable, and expressive behavior acquisition with minimum human effort. Unlike prior approaches that rely heavily on reward engineering, human demonstrations, motion capture, or expensive pairwise preference labels, LAPP leverages large language models (LLMs) to automatically generate preference labels from raw state-action trajectories collected during reinforcement learning (RL). These labels are used to train an online preference predictor, which in turn guides the policy optimization process toward satisfying high-level behavioral specifications provided by humans. Our key technical contribution is the integration of LLMs into the RL feedback loop through trajectory-level preference prediction, enabling robots to acquire complex skills including subtle control over gait patterns and rhythmic timing. We evaluate LAPP on a diverse set of quadruped locomotion and dexterous manipulation tasks and show that it achieves efficient learning, higher final performance, faster adaptation, and precise control of high-level behaviors. Notably, LAPP enables robots to master highly dynamic and expressive tasks such as quadruped backflips, which remain out of reach for standard LLM-generated or handcrafted rewards. Our results highlight LAPP as a promising direction for scalable preference-driven robot learning.
Abstract:We introduce ApolloRL, an open platform for research in reinforcement learning for autonomous driving. The platform provides a complete closed-loop pipeline with training, simulation, and evaluation components. It comes with 300 hours of real-world data in driving scenarios and popular baselines such as Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) agents. We elaborate in this paper on the architecture and the environment defined in the platform. In addition, we discuss the performance of the baseline agents in the ApolloRL environment.
Abstract:Training a deep object detector for autonomous driving requires a huge amount of labeled data. While recording data via on-board sensors such as camera or LiDAR is relatively easy, annotating data is very tedious and time-consuming, especially when dealing with 3D LiDAR points or radar data. Active learning has the potential to minimize human annotation efforts while maximizing the object detector's performance. In this work, we propose an active learning method to train a LiDAR 3D object detector with the least amount of labeled training data necessary. The detector leverages 2D region proposals generated from the RGB images to reduce the search space of objects and speed up the learning process. Experiments show that our proposed method works under different uncertainty estimations and query functions, and can save up to 60% of the labeling efforts while reaching the same network performance.
Abstract:Augmented reality (AR) displays become more and more popular recently, because of its high intuitiveness for humans and high-quality head-mounted display have rapidly developed. To achieve such displays with augmented information, highly accurate image registration or ego-positioning are required, but little attention have been paid for out-door environments. This paper presents a method for ego-positioning in outdoor environments with low cost monocular cameras. To reduce the computational and memory requirements as well as the communication overheads, we formulate the model compression algorithm as a weighted k-cover problem for better preserving model structures. Specifically for real-world vision-based positioning applications, we consider the issues with large scene change and propose a model update algorithm to tackle these problems. A long- term positioning dataset with more than one month, 106 sessions, and 14,275 images is constructed. Based on both local and up-to-date models constructed in our approach, extensive experimental results show that high positioning accuracy (mean ~ 30.9cm, stdev. ~ 15.4cm) can be achieved, which outperforms existing vision-based algorithms.