Safe motion planning in robotics requires planning into space which has been verified to be free of obstacles. However, obtaining such environment representations using lidars is challenging by virtue of the sparsity of their depth measurements. We present a learning-aided 3D lidar reconstruction framework that upsamples sparse lidar depth measurements with the aid of overlapping camera images so as to generate denser reconstructions with more definitively free space than can be achieved with the raw lidar measurements alone. We use a neural network with an encoder-decoder structure to predict dense depth images along with depth uncertainty estimates which are fused using a volumetric mapping system. We conduct experiments on real-world outdoor datasets captured using a handheld sensing device and a legged robot. Using input data from a 16-beam lidar mapping a building network, our experiments showed that the amount of estimated free space was increased by more than 40% with our approach. We also show that our approach trained on a synthetic dataset generalises well to real-world outdoor scenes without additional fine-tuning. Finally, we demonstrate how motion planning tasks can benefit from these denser reconstructions.

While an exciting diversity of new imaging devices is emerging that could dramatically improve robotic perception, the challenges of calibrating and interpreting these cameras have limited their uptake in the robotics community. In this work we generalise techniques from unsupervised learning to allow a robot to autonomously interpret new kinds of cameras. We consider emerging sparse light field (LF) cameras, which capture a subset of the 4D LF function describing the set of light rays passing through a plane. We introduce a generalised encoding of sparse LFs that allows unsupervised learning of odometry and depth. We demonstrate the proposed approach outperforming monocular, stereo and conventional techniques for dealing with 4D imagery, yielding more accurate odometry and depth maps and delivering these with metric scale. We anticipate our technique to generalise to a broad class of LF and sparse LF cameras, and to enable unsupervised recalibration for coping with shifts in camera behaviour over the lifetime of a robot. This work represents a first step toward streamlining the integration of new kinds of imaging devices in robotics applications.

Grasping objects in cluttered scenarios is a challenging task in robotics. Performing pre-grasp actions such as pushing and shifting to scatter objects is a way to reduce clutter. Based on deep reinforcement learning, we propose a Fast-Learning Grasping (FLG) framework, that can integrate pre-grasping actions along with grasping to pick up objects from cluttered scenarios with reduced real-world training time. We associate rewards for performing moving actions with the change of environmental clutter and utilize a hybrid triggering method, leading to data-efficient learning and synergy. Then we use the output of an extended fully convolutional network as the value function of each pixel point of the workspace and establish an accurate estimation of the grasp probability for each action. We also introduce a mask function as prior knowledge to enable the agents to focus on the accurate pose adjustment to improve the effectiveness of collecting training data and, hence, to learn efficiently. We carry out pre-training of the FLG over simulated environment, and then the learnt model is transferred to the real world with minimal fine-tuning for further learning during actions. Experimental results demonstrate a 94% grasp success rate and the ability to generalize to novel objects. Compared to state-of-the-art approaches in the literature, the proposed FLG framework can achieve similar or higher grasp success rate with lesser amount of training in the real world. Supplementary video is available at https://youtu.be/KTGj1fGU6ho.

This paper presents a pipeline for semantic segmentation of trees into their components. Given a single RGB-D image of a tree, we employ a deep network to predict labels to classify each pixel of the tree into trunk, branches, twigs and leaves. Multiple convolutional neural network architectures to combine the complementary modalities of depth and colour data are investigated. An asynchronous training approach where two networks trained separately on RGB and depth encoded as a 3-channel HHA image are combined using a late fusion architecture with different learning rates performs the best. Training and evaluation are performed on a synthetic dataset of 6 species of broadleaf trees. We further demonstrate the network's generalization capabilities, across various tree species on the synthetic dataset, achieving an accuracy of upto 92.5%. Furthermore, we present a qualitative evaluation of our approach on real-world data.

This paper presents underwater 3D capture using a commercial depth camera. Previous underwater capture systems use ordinary cameras, and it is well-known that a calibration procedure is needed to handle refraction. The same is true for a depth camera being used underwater. We describe a calibration method that corrects the depth maps of refraction effects. Another challenge is that depth cameras use infrared light (IR) which is heavily attenuated in water. We demonstrate scanning is possible with commercial depth cameras for ranges up to 20 cm in water. The motivation for using a depth camera under water is the same as in air — it provides dense depth data and higher quality 3D reconstruction than multi-view stereo. Underwater 3D capture is being increasingly used in marine biology and oceanology; our approach offers exciting prospects for such applications. To the best of our knowledge, ours is the first approach that successfully demonstrates underwater 3D capture using low cost depth cameras like Intel RealSense. We describe a complete system, including protective housing for the depth camera which is suitable for handheld use by a diver. Our main contribution is an easy-to-use calibration method, which we evaluate on exemplar data as well as 3D reconstructions in a lab aquarium. We also present initial results of ocean deployment.

This paper proposes a generalized algorithm that enables mobile agents to meet in a bounded region based only on bearing information of other agents within their vicinity. Each agent repeatedly employs a stop-and-go strategy consisting of the following three actions: (1) Estimate the bearing of agents in its vicinity, (2) compute a target point based on the estimates, and (3) move to that target point. The motivation and case study example is a modular robot, the Distributed Flight Array, which we employ to validate the proposed algorithm.

Human activity recognition is a thriving research field. There are lots of studies in different sub-areas of activity recognition proposing different methods. However, unlike other applications, there is lack of established benchmarking problems for activity recognition. Typically, each research group tests and reports the performance of their algorithms on their own datasets using experimental setups specially conceived for that specific purpose. In this work, we introduce a versatile human activity dataset conceived to fill that void. We illustrate its use by presenting comparative results of different classification techniques, and discuss about several metrics that can be used to assess their performance. Being an initial benchmarking, we expect that the possibility to replicate and outperform the presented results will contribute to further advances in state-of-the-art methods.