In this paper, we address the challenge of exploring unknown indoor environments using autonomous aerial robots with Size Weight and Power (SWaP) constraints. The SWaP constraints induce limits on mission time requiring efficiency in exploration. We present a novel exploration framework that uses Deep Learning (DL) to predict the most likely indoor map given the previous observations, and Deep Reinforcement Learning (DRL) for exploration, designed to run on modern SWaP constraints neural processors. The DL-based map predictor provides a prediction of the occupancy of the unseen environment while the DRL-based planner determines the best navigation goals that can be safely reached to provide the most information. The two modules are tightly coupled and run onboard allowing the vehicle to safely map an unknown environment. Extensive experimental and simulation results show that our approach surpasses state-of-the-art methods by 50-60% in efficiency, which we measure by the fraction of the explored space as a function of the trajectory length.

The challenge of mapping indoor environments is addressed. Typical heuristic algorithms for solving the motion planning problem are frontier-based methods, that are especially effective when the environment is completely unknown. However, in cases where prior statistical data on the environment's architectonic features is available, such algorithms can be far from optimal. Furthermore, their calculation time may increase substantially as more areas are exposed. In this paper we propose two means by which to overcome these shortcomings. One is the use of deep reinforcement learning to train the motion planner. The second is the inclusion of a pre-trained generative deep neural network, acting as a map predictor. Each one helps to improve the decision making through use of the learned structural statistics of the environment, and both, being realized as neural networks, ensure a constant calculation time. We show that combining the two methods can shorten the duration of the mapping process by up to 4 times, compared to frontier-based motion planning.

Our main technical result is that, in the coset leader graph of a linear binary code of block length n, the metric balls spanned by constant-weight vectors grow exponentially slower than those in (0, 11n. Following the approach of Friedman and Tillich, we use this fact to improve on the first linear programming bound on the rate of low-density parity check (LDPC) codes, as the function of their minimal relative distance. This improvement, combined with the techniques of Ben-Haim and Litsyn, improves the rate versus distance bounds for LDPC codes in a significant subrange of relative distances.

Brier et al (2006) showed how to attack RSA by induction of faults in public modulus n. We propose to use the same kind of technique to attack other asymmetric cryptographic schemes. The most interesting case in which we use a somewhat different approach is the attack on Elliptic Curves based signature protocol (namely ECDSA). Here we also take advantage of the short keys to offer a nontrivial practical attack that enables us to fully recover the private key. Different idea is used to attack Guillou-Quisquater authentication scheme (GQ). This demonstrates how the difference between schemes influences the details of the modulus corruption attacks. Special efforts were devoted to calculate the amount of corrupted data to perform the attack on each scheme. Various ways of protection against fault injection attacks on public key elements are discussed.