Predicting agents’ trajectories in complex environments is critical for achieving safe autonomous robot navigation. Empirically, agents’ decisions and preferences are susceptible to changes in environmental factors (e.g., interactions with other agents, weather conditions, traffic rules). State-of-the-art methods rely on High-Definition (HD) or semantic maps to model the environment, but do not take into account unpredictable factors such as complex weather conditions. In addition, since HD maps are nontrivial to obtain, those methods are limited in the scope of environments they can be applied in. We propose a more flexible graph based trajectory prediction model that uses only images to model the environment, without requiring expensive map information. We experimentally validate our proposed model, demonstrating robust performances in trajectory prediction compared to state-of-the-art methods, and outperform in complex environments that cannot be modeled with purely map based methods, such as diverse weather conditions.

Planning in unstructured environments is challenging - it relies on sensing, perception, scene reconstruction, and reasoning about various uncertainties. We propose DeepSemanticHPPC, a novel uncertainty-aware hypothesis-based planner for unstructured environments. Our algorithmic pipeline consists of: a deep Bayesian neural network which segments surfaces with uncertainty estimates; a flexible point cloud scene representation; a next-best-view planner which minimizes the uncertainty of scene semantics using sparse visual measurements; and a hypothesis-based path planner that proposes multiple kinematically feasible paths with evolving safety confidences given next-best-view measurements. Our pipeline iteratively decreases semantic uncertainty along planned paths, filtering out unsafe paths with high confidence. We show that our framework plans safe paths in real-world environments where existing path planners typically fail.

A novel automatic image annotation system is proposed, which integrates two sets of SVMs (support vector machines), namely the MIL-based (multiple instance learning) and global-feature-based SVMs, for annotation. The MIL-based features are obtained by applying MIL on the image blocks. They are further input to a set of SVMs for finding the optimum hyperplanes to categorize training images. Similarly, global color and texture features are fed into another set of SVMs for categorizing training images. Consequently, two sets of image features are constructed for each test image and are respectively sent to the two sets of SVMs, whose outputs are incorporated to obtain the final annotation results. Our system is validated using COREL images and outperforms the peer systems in terms of efficiency and accuracy.