Robust Spatial Perception for Autonomous Vehicles in the Wild
Autonomous driving, aka. mobile autonomy, promises to radically change the cityscape and save many human lives. A pillar component for achieving mobile autonomy is spatial perception - the ability for vehicles to understand the ambient environment and localize themselves on the road. Thanks to the recent advances in computer vision and solid-state technology, great improvement in spatial perception has been witnessed in controlled environments. Nevertheless, the perception robustness of many systems is still far off the safety requirement of autonomous driving when it comes to the wild condition, such as bad weather, poor illumination, various dynamic objects or even malicious attacks. In the MAPS lab, we study the robust spatial perception problems in full-stack, ranging from the single-modality based methods to multi-sensory fusion, and to the perception uncertainty quantification. More recently, a traction to my lab is unfolding the potential of 4D automotive radar in localization and scene understanding. As an emerging sensor, automotive radars are reputable for their sensing robustness against bad weather and adverse illumination. However, due to their significantly lower data quality, it remains largely unknown how one can transform the radar sensing robustness to vehicle perception effectiveness - a question my team keen to answer.
Robust and Rapid Sense Augmentation Support for First Responders
From the equator to the Arctic, fire disasters are going to happen more often as a result of anthropogenic climate change. This consequently results in more frequent duty calls of firefighters. However, at the present, firefighting is still regarded as one of the most strenuous and dangerous jobs in the world. A fire incident is often accompanied by a variety of airborne obscurants (e.g., smoke and dust) and poor illumination, making firefighters difficult to navigate themselves and understand the fire ground. We aim to design robust yet real-time localization, mapping and scene understanding services that can be directly integrated into the augmented reality wearables and firefighting robots. These support systems will, in turn, enhance firefighters’ operational capacity and safety in visually-degraded conditions and on resource-constrained platforms.
Media Exposure: BBC News, BBC Good Morning Scotland, STV, Planet Radio, Sky News, Evening Standard Tech & Science Daily, Scottish Daily Express, The Independent, Scottish Field, Scottish Daily Mail, Italy 24 News, Irish News, Engineering & Technology, Digit News
Privacy-aware Low-Cost Human Sensing
Despite a plethora of methods being proposed in the last decades, today’s human sensing (e.g., who, where, and what activities) systems are mostly dominant by RGB camera-based approaches that suffer from the adverse lighting conditions or privacy concerns in domestic environments. On the other side of the problem, unlike designing methods for cameras, it is much more challenging for us to find design heuristics for low-resolution sensors, e.g., mmWave, WiFi, UWB, BLE and inertial measurement units - as humans do not use these modalities to perceive the world, nor relate our everyday experience in improving the algorithm for these sensors. By exploiting the recent advances in machine learning, we advocate AI-empowered methods to model the data from these sensors and push their limits to the envelope. A related question also of our interest is - beyond the coarse-grained localization, is it possible to achieve fine-grained pose estimation (e.g., gesture and hand movement etc.) with these low-cost and low-resolution sensors?
Research Output: [Patterns’2023], [IoT-J’2023], [UbiComp’2022], [IoT-J’2022],[ICCV’2021], [TMC’2021], [TNNLS’2021], [ICRA’2020], [TMC’2019], [AAAI’2019], [DCOSS’2019], [AAAI’2018], [MobiCom’2018], [TWC’2016]
Robust Identity Inference across Digital and Physical Worlds (completed)
Key to realizing the vision of human-centred computing is the ability for machines to recognize people, so that spaces and devices can become truly personalized. However, the unpredictability of real-world environments impacts robust recognition, limiting usability. In real conditions, human identification systems have to handle issues such as out-of-set subjects and domain deviations, where conventional supervised learning approaches for training and inference are poorly suited. With the rapid development of Internet of Things (IoT), we advocate a new labelling method that exploits signals of opportunity hidden in heterogeneous IoT data. The key insight is that one sensor modality can leverage the signals measured by other co-located sensor modalities to improve its own labelling performance. If identity associations between heterogeneous sensor data can be discovered, it is possible to automatically label data, leading to more robust human recognition, without manual labelling or enrolment. On the other side of the coin, we also study the privacy implication for such cross-modal identity association.