This work addresses the challenge of personalizing trajectories generated in automated decision-making systems by introducing a resource-efficient approach that enables rapid adaptation to individual users' preferences. Our method leverages a pretrained conditional diffusion model with Preference Latent Embeddings (PLE), trained on a large, reward-free offline dataset. The PLE serves as a compact representation for capturing specific user preferences. By adapting the pretrained model using our proposed preference inversion method, which directly optimizes the learnable PLE, we achieve superior alignment with human preferences compared to existing solutions like Reinforcement Learning from Human Feedback (RLHF) and Low-Rank Adaptation (LoRA). To better reflect practical applications, we create a benchmark experiment using real human preferences on diverse, high-reward trajectories.

Deploying a safe mobile robot policy in scenarios with human pedestrians is challenging due to their unpredictable movements. Current Reinforcement Learningbased motion planners rely on a single policy to simulate pedestrian movements and could suffer from the over-fitting issue. Alternatively, framing the collision avoidance problem as a multi-agent framework, where agents generate dynamic movements while learning to reach their goals, can lead to conflicts with human pedestrians due to their homogeneity.To tackle this problem, we introduce an efficient method that enhances agent diversity within a single policy by maximizing an information-theoretic objective. This diversity enriches each agent’s experiences, improving its adaptability to unseen crowd behaviors. In assessing an agent’s robustness against unseen crowds, we propose diverse scenarios inspired by pedestrian crowd behaviors. Our behavior-conditioned policies outperform existing works in these challenging scenes, reducing potential collisions without additional time or travel.

Offline Reinforcement Learning (RL) offers an attractive alternative to interactive data acquisition by leveraging pre-existing datasets. However, its effectiveness hinges on the quantity and quality of the data samples. This work explores the use of more readily available, albeit off-dynamics datasets, to address the challenge of data scarcity in Offline RL. We propose a novel approach using conditional Diffusion Probabilistic Models (DPMs) to learn the joint distribution of the large-scale off-dynamics dataset and the limited target dataset. To enable the model to capture the underlying dynamics structure, we introduce two contexts for the conditional model: (1) a continuous dynamics score allows for partial overlap between trajectories from both datasets, providing the model with richer information; (2) an inverse-dynamics context guides the model to generate trajectories that adhere to the target environment’s dynamic constraints. Empirical results demonstrate that our method significantly outperforms several strong baselines. Ablation studies further reveal the critical role of each dynamics context. Additionally, our model demonstrates that by modifying the context, we can interpolate between source and target dynamics, making it more robust to subtle shifts in the environment.

In reinforcement learning with image-based inputs, it is crucial to establish a robust and generalizable state representation. Recent advancements in metric learning, such as deep bisimulation metric approaches, have shown promising results in learning structured low-dimensional representation space from pixel observations, where the distance between states is measured based on task-relevant features. However, these approaches face challenges in demanding generalization tasks and scenarios with non-informative rewards. This is because they fail to capture sufficient long-term information in the learned representations. To address these challenges, we propose a novel State Chrono Representation (SCR) approach. SCR augments state metric-based representations by incorporating extensive temporal information into the update step of bisimulation metric learning. It learns state distances within a temporal framework that considers both future dynamics and cumulative rewards over current and long-term future states. Our learning strategy effectively incorporates future behavioral information into the representation space without introducing a significant number of additional parameters for modeling dynamics. Extensive experiments conducted in DeepMind Control and Meta-World environments demonstrate that SCR achieves better performance comparing to other recent metric-based methods in demanding generalization tasks. The codes of SCR are available in https://github.com/jianda-chen/SCR.

For the distant speech recognition, the multi-channel processing has been proven to significantly improve the ASR performances compared to the single channel approaches. However, there is very little work has done to provide a comparative evaluation of the approaches, particularly with the modern Deep Neural Network (DNN) recognizers. In this paper, we address the above problem by evaluating the most recently reported mutti-channel methods for the distant speech recognition under urban environments using the 3rd CHiME Challenge database. Particularly, we analyse the effects of each stage of processing of beamforming, adaptive noise cancellation and dereverberation. The back-end processing components are also investigated. We further describe in details our best performing system which combines a harmonic to subharmonic ratio (SHR) voice activity detection, and correlative beamforming with adaptive channel selection in the from-end; semi-supervised DNN adaptation and RNN language model rescoring in the back-end. The system achieved impressive 60% and 55% relative WER reductions on the development set, as well as 65% and 60% of the same on the test set, for real and simulated data sets, respectively.

In previous works, we have developed a spectrogram image feature extraction framework for robust sound event recognition. The basic idea here is to extract useful information from the 2D time-frequency representation of the sound signal to build up specific feature extractions and classifier under noisy conditions. In this paper, we propose a novel robust spectrogram image method where the key is the observed sparsity of the sound spectrogram image in wavelet representations, which is modeled by the Generalized Gaussian Distributions modeling. Furthermore, the Generalized Gaussian Distribution Kullback-Leibler (GGD-KL) kernel SVM is developed to embed the given probabilistic distance into the quadratic programming machine to optimize the classification The experimental result shows the superiority of the proposed method to the previous works and the state-of-the-art in the field.

This paper describes the gesture recognition system developed by the Institute for Infocomm Research (I2R) for the 2013 ICMI CHALEARN Multi-modal Gesture Recognition Challenge. The proposed system adopts a multi-modal approach for detecting as well as recognizing the gestures. Automated gesture detection is performed using both audio signals and information about hand joints obtained from the Kinect sensor to segment a sample into individual gestures. Once the gestures are detected and segmented, features extracted from three different modalities, namely, audio, 2-dimensional video (RGB), and skeletal joints (Kinect) are used to classify a given sequence of frames into one of the 20 known gestures or an unrecognized gesture. Mel frequency cepstral coefficients (MFCC) are extracted from the audio signals and a Hidden Markov Model (HMM) is used for classification. While Space-Time Interest Points (STIP) are used to represent the RGB modality, a covariance descriptor is extracted from the skeletal joint data. In the case of both RGB and Kinect modalities, Support Vector Machines (SVM) are used for gesture classification. Finally, a fusion scheme is applied to accumulate evidence from all the three modalities and predict the sequence of gestures in each test sample. The proposed gesture recognition system is able to achieve an average edit distance of 0.2074 over the 275 test samples containing 2,742 unlabeled gestures. While the proposed system is able to recognize the known gestures with high accuracy, most of the errors are caused due to insertion, which occurs when an unrecognized gesture is misclassified as one of the 20 known gestures.