Researchers at Carnegie Mellon University's School of Computer Science and the University of California, Berkeley, have designed a robotic system that enables a low-cost and relatively small legged robot to climb and descend stairs nearly its height; traverse rocky, slippery, uneven, steep and varied terrain; walk across gaps; scale rocks and curbs; and even operate in the dark. "Empowering small robots to climb stairs and handle a variety of environments is crucial to developing robots that will be useful in people's homes as well as search-and-rescue operations," said Deepak Pathak, an assistant professor in the Robotics Institute. "This system creates a robust and adaptable robot that could perform many everyday tasks." The team put the robot through its paces, testing it on uneven stairs and hillsides at public parks, challenging it to walk across stepping stones and over slippery surfaces, and asking it to climb stairs that for its height would be akin to a human leaping over a hurdle. The researchers trained the robot with 4,000 clones of it in a simulator, where they practiced walking and climbing on challenging terrain.

Prime Minister Narendra Modi inaugurated the 25th edition of Bengaluru Tech Summit 2022, at a glittering ceremony in the presence of a galaxy of leaders from the IT, BT and start-up sectors. The event was organized by The Department of Electronics, IT, Bt, S&T, Government of Karnataka along with Software Technology Parks of India (STPI), and is the first full-fledged on ground version of BTS post the pandemic. The central theme of BTS this year is'Tech4NexGen' and will focus on Electronics, IT, Deep Tech, Biotech, and Startups. The inaugural ceremony was graced by the Guests of Honor H.E Mr. Petri Honkonen, Minister of Science & Culture, Finland, H.E. Mr. Omar Bin Sultan Al Olama, Minister of State for Artificial Intelligence, Digital Economy & Remote Work Applications, United Arab Emirates, H.E. Mr. Tim Watts, Assistant Minister for Foreign Affairs, Australia. The ceremony was presided over by Shri Basavaraj S. Bommai, Chief Minister of Karnataka.

Tuvalu's foreign minister, Simon Kofe, told the COP27 climate summit yesterday that Tuvalu would look to the metaverse to preserve its culture and history. With global temperatures expected to rise as much as 2.8 degrees Celsius by the end of the century, the Pacific island nation is particularly vulnerable to rising sea levels. At last year's COP26 summit, Kofe addressed the conference while standing knee-deep in seawater to highlight the climate change threat. Climate scientists anticipate the entire country will be underwater by the end of the 21st century. Addressing the climate summit, Kofe said: "As our land disappears, we have no choice but to become the world's first digital nation. Our land, our ocean, our culture are the most precious assets of our people. And to keep them safe from harm, no matter what happens in the physical world, we'll move them to the cloud."

In 2015, I visited Fiji, Kiribati, and Tuvalu, which had just been hit by a cyclone. There, I learned a slogan -- "1.5 to stay alive" -- which refers to the 1.5 degrees Celsius (2.7 degrees Fahrenheit) threshold for global warming that, in theory, would avoid disastrous consequences. People living on the Pacific islands are well aware of the grave threat to humanity posed by climate change. Six months later, I met these new comrades again at climate negotiations in Paris. While speaking at an event, I referred to "1.5 to stay alive".

Relational triple extraction is challenging for its difficulty in capturing rich correlations between entities and relations. Existing works suffer from 1) heterogeneous representations of entities and relations, and 2) heterogeneous modeling of entity-entity interactions and entity-relation interactions. Therefore, the rich correlations are not fully exploited by existing works. In this paper, we propose UniRel to address these challenges. Specifically, we unify the representations of entities and relations by jointly encoding them within a concatenated natural language sequence, and unify the modeling of interactions with a proposed Interaction Map, which is built upon the off-the-shelf self-attention mechanism within any Transformer block. With comprehensive experiments on two popular relational triple extraction datasets, we demonstrate that UniRel is more effective and computationally efficient. The source code is available at https://github.com/wtangdev/UniRel.

Point clouds are a widely available and canonical data modality which convey the 3D geometry of a scene. Despite significant progress in classification and segmentation from point clouds, policy learning from such a modality remains challenging, and most prior works in imitation learning focus on learning policies from images or state information. In this paper, we propose a novel framework for learning policies from point clouds for robotic manipulation with tools. We use a novel neural network, ToolFlowNet, which predicts dense per-point flow on the tool that the robot controls, and then uses the flow to derive the transformation that the robot should execute. We apply this framework to imitation learning of challenging deformable object manipulation tasks with continuous movement of tools, including scooping and pouring, and demonstrate significantly improved performance over baselines which do not use flow. We perform 50 physical scooping experiments with ToolFlowNet and attain 82% scooping success. See https://tinyurl.com/toolflownet for supplementary material.

The advancement of deep learning has led to the development of neural decoders for low latency communications. However, neural decoders can be very complex which can lead to increased computation and latency. We consider iterative pruning approaches (such as the lottery ticket hypothesis algorithm) to prune weights in neural decoders. Decoders with fewer number of weights can have lower latency and lower complexity while retaining the accuracy of the original model. This will make neural decoders more suitable for mobile and other edge devices with limited computational power. We also propose semi-soft decision decoding for neural decoders which can be used to improve the bit error rate performance of the pruned network.

Bayesian optimization (BO) is a class of popular methods for expensive black-box optimization, and has been widely applied to many scenarios. However, BO suffers from the curse of dimensionality, and scaling it to high-dimensional problems is still a challenge. In this paper, we propose a variable selection method MCTS-VS based on Monte Carlo tree search (MCTS), to iteratively select and optimize a subset of variables. That is, MCTS-VS constructs a low-dimensional subspace via MCTS and optimizes in the subspace with any BO algorithm. We give a theoretical analysis of the general variable selection method to reveal how it can work. Experiments on high-dimensional synthetic functions and real-world problems (i.e., NAS-bench problems and MuJoCo locomotion tasks) show that MCTS-VS equipped with a proper BO optimizer can achieve state-of-the-art performance.

Amazon, Nimble, Plus One, Waymo, and Zoox use remote human supervision of robot fleets in applications ranging from self-driving taxis to automated warehouse fulfillment [1, 2, 3, 4, 5]. These robots intermittently cede control during task execution to remote human supervisors for corrective interventions. The interventions take place either during learning, when they are used to improve the robot policy, or during execution, when the policy is no longer updated but robots can still request human assistance when needed to improve reliability. In the continual learning setting, these occur simultaneously: the robot policy has been deployed but continues to be updated indefinitely with additional intervention data. Furthermore, any individual robot can share its intervention data with the rest of the fleet. As opposed to robot swarms that must coordinate with each other to achieve a common objective, a robot fleet is a set of independent robots simultaneously executing the same control policy in parallel environments. We refer to the setting of a robot fleet learning via interactive requests for human supervision (see Figure 1) as Interactive Fleet Learning (IFL). Of central importance in IFL is the supervisor allocation problem: how should limited human supervision be allocated to robots in a manner that maximizes the throughput of the fleet?

In recent years, the machine learning research landscape has been reshaped by the growth of Chinese AI research. China now consistently stands as the second-largest country in terms of total publications at NeurIPS, after the United States. In 2020, papers from Chinese institutions represented 13.6% of all NeurIPS publications [6]. The following year, this share increased to 17.5%, representing a relative increase of 28.7% [13].