This paper develops upper bounds on the end-to-end transmission capacity of
multi-hop wireless networks. Potential source-destination paths are dynamically
selected from a pool of randomly located relays, from which a closed-form lower
bound on the outage probability is derived in terms of the expected number of
potential paths. This is in turn used to provide an upper bound on the number
of successful transmissions that can occur per unit area, which is known as the
transmission capacity. The upper bound results from assuming independence among
the potential paths, and can be viewed as the maximum diversity case. A useful
aspect of the upper bound is its simple form for an arbitrary-sized network,
which allows insights into how the number of hops and other network parameters
affect spatial throughput in the non-asymptotic regime. The outage probability
analysis is then extended to account for retransmissions with a maximum number
of allowed attempts. In contrast to prevailing wisdom, we show that
predetermined routing (such as nearest-neighbor) is suboptimal, since more hops
are not useful once the network is interference-limited. Our results also make
clear that randomness in the location of relay sets and dynamically varying
channel states is helpful in obtaining higher aggregate throughput, and that
dynamic route selection should be used to exploit path diversity.