Related papers: Connectivity-Aware Representations for Constrained…

Training and inference on edge devices often requires an efficient setup due to computational limitations. While pre-computing data representations and caching them on a server can mitigate extensive edge device computation, this leads to…

Unsupervised pre-training has been proven as an effective approach to boost various downstream tasks given limited labeled data. Among various methods, contrastive learning learns a discriminative representation by constructing positive and…

Uncertain dynamic obstacles, such as pedestrians or vehicles, pose a major challenge for optimal robot navigation with safety guarantees. Previous work on motion planning has followed two main strategies to provide a safe bound on an…

Incorporating encoding-decoding nets with adversarial nets has been widely adopted in image generation tasks. We observe that the state-of-the-art achievements were obtained by carefully balancing the reconstruction loss and adversarial…

Sampling-based algorithms are widely used for motion planning in high-dimensional configuration spaces. However, due to low sampling efficiency, their performance often diminishes in complex configuration spaces with narrow corridors.…

We revisit previous contrastive learning frameworks to investigate the effect of introducing an adaptive margin into the contrastive loss function for time series representation learning. Specifically, we explore whether an adaptive margin…

Self-supervised representation learning for point cloud videos remains a challenging problem with two key limitations: (1) existing methods rely on explicit knowledge to learn motion, resulting in suboptimal representations; (2) prior…

This paper studies a federated edge learning system, in which an edge server coordinates a set of edge devices to train a shared machine learning model based on their locally distributed data samples. During the distributed training, we…

Multimodal contrastive learning is a methodology for linking different data modalities; the canonical example is linking image and text data. The methodology is typically framed as the identification of a set of encoders, one for each…

The well-established modular autonomous driving system is decoupled into different standalone tasks, e.g. perception, prediction and planning, suffering from information loss and error accumulation across modules. In contrast, end-to-end…

Federated learning (FL) enables collaborative model training across distributed devices without sharing raw data, but applying FL to multi-modal settings introduces significant challenges. Clients typically possess heterogeneous modalities…

Many real-world walking scenarios contain obstacles and unsafe ground patches (e.g., slippery or cluttered areas), leaving a disconnected set of admissible footholds that can be modeled as stepping-stone-like regions. We propose an onboard,…

The compressive learning framework reduces the computational cost of training on large-scale datasets. In a sketching phase, the data is first compressed to a lightweight sketch vector, obtained by mapping the data samples through a…

An energy-based model (EBM) is a popular generative framework that offers both explicit density and architectural flexibility, but training them is difficult since it is often unstable and time-consuming. In recent years, various training…

To reduce the computational cost of humanoid motion generation, we introduce a new approach to representing robot kinematic reachability: the differentiable reachability map. This map is a scalar-valued function defined in the task space…

Skill-based reinforcement learning (SBRL) enables rapid adaptation in environments with sparse rewards by pretraining a skill-conditioned policy. Effective skill learning requires jointly maximizing both exploration and skill diversity.…

Goal-Conditioned Reinforcement Learning (GCRL) can enable agents to spontaneously set diverse goals to learn a set of skills. Despite the excellent works proposed in various fields, reaching distant goals in temporally extended tasks…

While raw images have distinct advantages over sRGB images, e.g., linearity and fine-grained quantization levels, they are not widely adopted by general users due to their substantial storage requirements. Very recent studies propose to…

This paper presents a novel method to generate spatial constraints for motion planning in dynamic environments. Motion planning methods for autonomous driving and mobile robots typically need to rely on the spatial constraints imposed by a…

While supervised learning is widely used for perception modules in conventional autonomous driving solutions, scalability is hindered by the huge amount of data labeling needed. In contrast, while end-to-end architectures do not require…