Getting acquainted with npj Robotics

Attitude can be extracted from optic flow when combined with a motion model that relates attitude to acceleration direction, which leads to stable flight attitude control with slight oscillations due to unobservable conditions.

Changing weather conditions pose a challenge for autonomous vehicles. Almalioglu and colleagues use a geometry-aware learning technique that fuses visual, lidar and radar information, such that the benefits of each can be used under different weather conditions.

Navigation and trajectory planning in environments with background flow, relevant for robotics, are challenging provided information only on local surrounding. The authors propose a reinforcement learning approach for time-efficient navigation of a swimmer through unsteady two-dimensional flows.

The authors propose a new framework, deep evolutionary reinforcement learning, evolves agents with diverse morphologies to learn hard locomotion and manipulation tasks in complex environments, and reveals insights into relations between environmental physics, embodied intelligence, and the evolution of rapid learning.

Off-line neuro-evolution produces robot swarms whose good performance in simulation does not often transfer to the real word. With an extensive empirical study, Hasselmann et al. substantiate overfitting as the dominant cause.

Bats with sophisticated biosonar systems move their ears at a high speed to help localize sound sources. Yin and Müller present a system inspired by this strategy, which can localize sounds with high accuracy and with a single detector, using a flexible silicone model of a bat’s ear and a deep convolutional neural network to process the complex Doppler signatures.

Autonomous flight is challenging for small flying robots, given the limited space for sensors and on-board processing capabilities, but a promising approach is to mimic optical-flow-based strategies of flying insects. A new development improves this technique, enabling smoother landings and better obstacle avoidance, by giving robots the ability to learn to estimate distances to objects by their visual appearance.

A reinforcement learning approach allows a suitably equipped glider to navigate thermal plumes autonomously in an open field.

A grand challenge in robotics is realising intelligent agents capable of autonomous interaction with the environment. In this Perspective, the authors discuss the potential, challenges and future direction of research aimed at demonstrating embodied intelligent robotics via neuromorphic technology.

Development of real-time sensing capability in artificial vision system requires an integration that allow sensing, computation, and storage, whilst remain energy efficient and compact. Here, the authors mimic the lobula giant movement detector to achieve this objective via light-mediated threshold switching memristor.

Sensory information processing in robots relies on a centralized approach with issues of wiring, fault-tolerance and latency. Here, the authors report a decentralized neuromorphic approach with self-healable memristive elements enabling intelligent sensations in a prototypical robotic nervous system.

Inspired by fast running cheetahs, the authors present a class of small-scale soft electromagnetic robots able to reach ultra-high running speeds of 70 BL/s (body lengths per second) as well as the ability to swim, jump, steer and transport cargo.

Modular robots with reconfigurable architectures show advantages in unpredicted environments. Here Yang et al. propose a heterogeneous assembly concept for cellular robot construction at millimeter scales, which can simultaneously reconfigure their morphologies and behaviours to conduct versatile tasks on demand.

A comparison of the energetics of jumping between biological and engineered systems shows that engineered systems can greatly increase energy limits using the process of work multiplication, and this analysis leads to the demonstration of a 30-centimetre device jumping over 30 metres.

Miniaturized systems for in situ plant applications are important to understand and preserve natural ecosystems. Here, the attachment of bioinspired microhooks to the surfaces of plant leaves is investigated, and on-leaf soft machines fabricated for monitoring conditions and for molecular delivery.

The morphology of a robot determines how efficiently it can traverse different terrain. Nygaard and colleagues present here a robot that can adapt it’s morphology when it is detecting different terrain and learn which configuration is most effective.

Sustained flight of an insect-sized flapping-wing aerial vehicle weighing just 259 milligrams that does not need to fly tethered to an off-board power supply is demonstrated.

Inspired by biological systems, engineers are exploring origami folding with smart material actuation to enable intrinsically actuated designs with complex functionalities and easy fabrication. This Review highlights recent advances in the design, fabrication and control of these origami robots.

This Review Article examines the development of functional untethered soft robotics, evaluating recent advances in soft robotic actuation, sensing, and integration in relation to untethered systems.